Compare commits
6 Commits
ui-tweaks/
...
7d3021efbf
| Author | SHA1 | Date | |
|---|---|---|---|
| 7d3021efbf | |||
| 23d208a5b7 | |||
|
00c9144010 | ||
|
|
44c02b45b4 | ||
|
|
5fb3b984b6 | ||
| 6f49533c94 |
@@ -1,31 +0,0 @@
|
|||||||
{
|
|
||||||
"permissions": {
|
|
||||||
"allow": [
|
|
||||||
"WebFetch(domain:github.com)",
|
|
||||||
"WebFetch(domain:www.sreality.cz)",
|
|
||||||
"WebFetch(domain:webscraping.pro)",
|
|
||||||
"WebFetch(domain:raw.githubusercontent.com)",
|
|
||||||
"Bash(python3:*)",
|
|
||||||
"Bash(open:*)",
|
|
||||||
"WebFetch(domain:www.realingo.cz)",
|
|
||||||
"WebFetch(domain:api.realingo.cz)",
|
|
||||||
"Bash(curl:*)",
|
|
||||||
"Bash(grep:*)",
|
|
||||||
"WebFetch(domain:www.realitni-pes.cz)",
|
|
||||||
"WebFetch(domain:www.bezrealitky.cz)",
|
|
||||||
"WebFetch(domain:apify.com)",
|
|
||||||
"WebFetch(domain:www.bezrealitky.com)",
|
|
||||||
"WebFetch(domain:reality.idnes.cz)",
|
|
||||||
"Bash(# Final checks: robots.txt and response time for rate limiting clues curl -s -L -H \"\"User-Agent: Mozilla/5.0 \\(Windows NT 10.0; Win64; x64\\) AppleWebKit/537.36 \\(KHTML, like Gecko\\) Chrome/120.0.0.0 Safari/537.36\"\" \"\"https://reality.idnes.cz/robots.txt\"\")",
|
|
||||||
"WebFetch(domain:www.cityhome.cz)",
|
|
||||||
"WebFetch(domain:www.psn.cz)",
|
|
||||||
"WebFetch(domain:www.city-home.cz)",
|
|
||||||
"WebFetch(domain:psn.cz)",
|
|
||||||
"WebFetch(domain:api.psn.cz)",
|
|
||||||
"Bash(done)",
|
|
||||||
"Bash(# Final summary: count total units across all projects\n# Get the total count from the unitsCountData we already extracted\necho \"\"From unitsCountData on /prodej page:\"\"\necho \"\" type_id 0 \\(Prodej bytů a ateliérů\\): 146\"\"\necho \"\" type_id 1 \\(Prodej komerčních nemovitostí\\): 14\"\"\necho \"\" type_id 2 \\(Pronájem bytů\\): 3\"\"\necho \"\" type_id 3 \\(Pronájem komerčních nemovitostí\\): 48\"\"\necho \"\"\"\"\necho \"\"Total for-sale projects: 19\"\"\necho \"\"\"\"\necho \"\"Disposition counts from the data:\"\"\npython3 << 'PYEOF'\n# Extract disposition counts from prodej page\nimport re\n\nwith open\\('/tmp/psn_prodej_p1.html', 'r', encoding='utf-8'\\) as f:\n html = f.read\\(\\)\n\n# Find disposition data\nidx = html.find\\('\\\\\\\\\"disposition\\\\\\\\\":['\\)\nif idx >= 0:\n chunk = html[idx:idx+2000].replace\\('\\\\\\\\\"', '\"'\\)\n # Extract name and count pairs\n import re\n pairs = re.findall\\(r'\"name\":\"\\([^\"]+\\)\",\"count\":\\(\\\\d+\\)', chunk\\)\n for name, count in pairs:\n print\\(f\" {name}: {count}\"\\)\nPYEOF)",
|
|
||||||
"Bash(ls:*)",
|
|
||||||
"Bash(chmod:*)"
|
|
||||||
]
|
|
||||||
}
|
|
||||||
}
|
|
||||||
5
.gitignore
vendored
5
.gitignore
vendored
@@ -1,3 +1,8 @@
|
|||||||
.vscode/
|
.vscode/
|
||||||
__pycache__/
|
__pycache__/
|
||||||
|
.DS_Store
|
||||||
byty_*.json
|
byty_*.json
|
||||||
|
*.json
|
||||||
|
*.log
|
||||||
|
mapa_bytu.html
|
||||||
|
|
||||||
|
|||||||
30
Makefile
30
Makefile
@@ -3,9 +3,13 @@ CONTAINER_NAME := maru-hleda-byt
|
|||||||
VOLUME_NAME := maru-hleda-byt-data
|
VOLUME_NAME := maru-hleda-byt-data
|
||||||
VALIDATION_CONTAINER := maru-hleda-byt-validation
|
VALIDATION_CONTAINER := maru-hleda-byt-validation
|
||||||
VALIDATION_VOLUME := maru-hleda-byt-validation-data
|
VALIDATION_VOLUME := maru-hleda-byt-validation-data
|
||||||
|
DEBUG_CONTAINER := maru-hleda-byt-debug
|
||||||
|
DEBUG_VOLUME := maru-hleda-byt-debug-data
|
||||||
|
DEBUG_PORT ?= 8082
|
||||||
PORT := 8080
|
PORT := 8080
|
||||||
|
SERVER_PORT ?= 8080
|
||||||
|
|
||||||
.PHONY: build run stop logs scrape restart clean help validation validation-local validation-stop validation-local-debug
|
.PHONY: build run stop logs scrape restart clean help serve validation validation-local validation-stop validation-local-debug debug debug-stop
|
||||||
|
|
||||||
help:
|
help:
|
||||||
@echo "Available targets:"
|
@echo "Available targets:"
|
||||||
@@ -20,6 +24,9 @@ help:
|
|||||||
@echo " validation-local-debug - Run validation locally with DEBUG logging"
|
@echo " validation-local-debug - Run validation locally with DEBUG logging"
|
||||||
@echo " restart - Restart the container (stop and run again)"
|
@echo " restart - Restart the container (stop and run again)"
|
||||||
@echo " clean - Stop container and remove the Docker image"
|
@echo " clean - Stop container and remove the Docker image"
|
||||||
|
@echo " serve - Start server.py locally on port 8080"
|
||||||
|
@echo " debug - Build and run debug Docker container with limited scrape (port $(DEBUG_PORT))"
|
||||||
|
@echo " debug-stop - Stop and remove the debug Docker container"
|
||||||
@echo " help - Show this help message"
|
@echo " help - Show this help message"
|
||||||
|
|
||||||
build:
|
build:
|
||||||
@@ -59,6 +66,27 @@ validation-stop:
|
|||||||
@docker rm $(VALIDATION_CONTAINER) 2>/dev/null || true
|
@docker rm $(VALIDATION_CONTAINER) 2>/dev/null || true
|
||||||
@echo "Validation container stopped and removed"
|
@echo "Validation container stopped and removed"
|
||||||
|
|
||||||
|
debug: build
|
||||||
|
@docker stop $(DEBUG_CONTAINER) 2>/dev/null || true
|
||||||
|
@docker rm $(DEBUG_CONTAINER) 2>/dev/null || true
|
||||||
|
docker run -d --name $(DEBUG_CONTAINER) \
|
||||||
|
-p $(DEBUG_PORT):8080 \
|
||||||
|
-v $(DEBUG_VOLUME):/app/data \
|
||||||
|
-e LOG_LEVEL=DEBUG \
|
||||||
|
$(IMAGE_NAME)
|
||||||
|
@sleep 2
|
||||||
|
docker exec $(DEBUG_CONTAINER) bash /app/run_all.sh --max-pages 1 --max-properties 10
|
||||||
|
@echo "Debug app at http://localhost:$(DEBUG_PORT)/mapa_bytu.html"
|
||||||
|
@echo "Debug status at http://localhost:$(DEBUG_PORT)/scrapers-status"
|
||||||
|
|
||||||
|
debug-stop:
|
||||||
|
@docker stop $(DEBUG_CONTAINER) 2>/dev/null || true
|
||||||
|
@docker rm $(DEBUG_CONTAINER) 2>/dev/null || true
|
||||||
|
@echo "Debug container stopped and removed"
|
||||||
|
|
||||||
|
serve:
|
||||||
|
DATA_DIR=. SERVER_PORT=$(SERVER_PORT) python3 server.py
|
||||||
|
|
||||||
validation-local:
|
validation-local:
|
||||||
./run_all.sh --max-pages 1 --max-properties 10
|
./run_all.sh --max-pages 1 --max-properties 10
|
||||||
|
|
||||||
|
|||||||
@@ -5,12 +5,14 @@ RUN apk add --no-cache curl bash tzdata \
|
|||||||
&& echo "Europe/Prague" > /etc/timezone
|
&& echo "Europe/Prague" > /etc/timezone
|
||||||
|
|
||||||
ENV PYTHONUNBUFFERED=1
|
ENV PYTHONUNBUFFERED=1
|
||||||
|
ENV DATA_DIR=/app/data
|
||||||
|
|
||||||
WORKDIR /app
|
WORKDIR /app
|
||||||
|
|
||||||
COPY scrape_and_map.py scrape_realingo.py scrape_bezrealitky.py \
|
COPY scrape_and_map.py scrape_realingo.py scrape_bezrealitky.py \
|
||||||
scrape_idnes.py scrape_psn.py scrape_cityhome.py \
|
scrape_idnes.py scrape_psn.py scrape_cityhome.py \
|
||||||
merge_and_map.py regen_map.py run_all.sh ratings_server.py ./
|
merge_and_map.py regen_map.py generate_status.py scraper_stats.py \
|
||||||
|
run_all.sh server.py ./
|
||||||
|
|
||||||
COPY build/crontab /etc/crontabs/root
|
COPY build/crontab /etc/crontabs/root
|
||||||
COPY build/entrypoint.sh /entrypoint.sh
|
COPY build/entrypoint.sh /entrypoint.sh
|
||||||
@@ -18,7 +20,7 @@ RUN chmod +x /entrypoint.sh run_all.sh
|
|||||||
|
|
||||||
RUN mkdir -p /app/data
|
RUN mkdir -p /app/data
|
||||||
|
|
||||||
EXPOSE 8080 8081
|
EXPOSE 8080
|
||||||
|
|
||||||
HEALTHCHECK --interval=60s --timeout=5s --start-period=300s \
|
HEALTHCHECK --interval=60s --timeout=5s --start-period=300s \
|
||||||
CMD wget -q -O /dev/null http://localhost:8080/ || exit 1
|
CMD wget -q -O /dev/null http://localhost:8080/ || exit 1
|
||||||
|
|||||||
@@ -1 +1 @@
|
|||||||
0 6,18 * * * cd /app && bash /app/run_all.sh >> /proc/1/fd/1 2>> /proc/1/fd/2
|
0 */4 * * * cd /app && bash /app/run_all.sh >> /proc/1/fd/1 2>> /proc/1/fd/2
|
||||||
|
|||||||
@@ -1,7 +1,7 @@
|
|||||||
#!/bin/bash
|
#!/bin/bash
|
||||||
set -euo pipefail
|
set -euo pipefail
|
||||||
|
|
||||||
DATA_DIR="/app/data"
|
export DATA_DIR="/app/data"
|
||||||
|
|
||||||
# Create symlinks so scripts (which write to /app/) persist data to the volume
|
# Create symlinks so scripts (which write to /app/) persist data to the volume
|
||||||
for f in byty_sreality.json byty_realingo.json byty_bezrealitky.json \
|
for f in byty_sreality.json byty_realingo.json byty_bezrealitky.json \
|
||||||
@@ -18,8 +18,5 @@ crond -b -l 2
|
|||||||
echo "[entrypoint] Starting initial scrape in background..."
|
echo "[entrypoint] Starting initial scrape in background..."
|
||||||
bash /app/run_all.sh &
|
bash /app/run_all.sh &
|
||||||
|
|
||||||
echo "[entrypoint] Starting ratings API server on port 8081..."
|
echo "[entrypoint] Starting server on port 8080..."
|
||||||
DATA_DIR="$DATA_DIR" python3 /app/ratings_server.py &
|
exec python3 /app/server.py
|
||||||
|
|
||||||
echo "[entrypoint] Starting HTTP server on port 8080..."
|
|
||||||
exec python3 -m http.server 8080 --directory "$DATA_DIR"
|
|
||||||
|
|||||||
@@ -1,427 +0,0 @@
|
|||||||
[
|
|
||||||
{
|
|
||||||
"hash_id": 990183,
|
|
||||||
"name": "Prodej bytu 3+kk 86 m²",
|
|
||||||
"price": 10385000,
|
|
||||||
"price_formatted": "10 385 000 Kč",
|
|
||||||
"locality": "Ke Tvrzi, Praha - Královice",
|
|
||||||
"lat": 50.0390519,
|
|
||||||
"lon": 14.63862,
|
|
||||||
"disposition": "3+kk",
|
|
||||||
"floor": 2,
|
|
||||||
"area": 86,
|
|
||||||
"building_type": "Cihlová",
|
|
||||||
"ownership": "Osobní",
|
|
||||||
"url": "https://www.bezrealitky.cz/nemovitosti-byty-domy/990183-nabidka-prodej-bytu-ke-tvrzi-praha",
|
|
||||||
"source": "bezrealitky",
|
|
||||||
"image": ""
|
|
||||||
},
|
|
||||||
{
|
|
||||||
"hash_id": 989862,
|
|
||||||
"name": "Prodej bytu 3+kk 73 m²",
|
|
||||||
"price": 12790000,
|
|
||||||
"price_formatted": "12 790 000 Kč",
|
|
||||||
"locality": "Vrázova, Praha - Smíchov",
|
|
||||||
"lat": 50.0711312,
|
|
||||||
"lon": 14.4076652,
|
|
||||||
"disposition": "3+kk",
|
|
||||||
"floor": 3,
|
|
||||||
"area": 73,
|
|
||||||
"building_type": "Cihlová",
|
|
||||||
"ownership": "Osobní",
|
|
||||||
"url": "https://www.bezrealitky.cz/nemovitosti-byty-domy/989862-nabidka-prodej-bytu-vrazova-praha",
|
|
||||||
"source": "bezrealitky",
|
|
||||||
"image": ""
|
|
||||||
},
|
|
||||||
{
|
|
||||||
"hash_id": 981278,
|
|
||||||
"name": "Prodej bytu 3+kk 70 m²",
|
|
||||||
"price": 11890000,
|
|
||||||
"price_formatted": "11 890 000 Kč",
|
|
||||||
"locality": "Argentinská, Praha - Holešovice",
|
|
||||||
"lat": 50.1026043,
|
|
||||||
"lon": 14.4435365,
|
|
||||||
"disposition": "3+kk",
|
|
||||||
"floor": 3,
|
|
||||||
"area": 70,
|
|
||||||
"building_type": "Cihlová",
|
|
||||||
"ownership": "Osobní",
|
|
||||||
"url": "https://www.bezrealitky.cz/nemovitosti-byty-domy/981278-nabidka-prodej-bytu-argentinska-praha",
|
|
||||||
"source": "bezrealitky",
|
|
||||||
"image": ""
|
|
||||||
},
|
|
||||||
{
|
|
||||||
"hash_id": 989817,
|
|
||||||
"name": "Prodej bytu 3+kk 88 m²",
|
|
||||||
"price": 13490000,
|
|
||||||
"price_formatted": "13 490 000 Kč",
|
|
||||||
"locality": "Miroslava Hajna, Praha - Letňany",
|
|
||||||
"lat": 50.1406487,
|
|
||||||
"lon": 14.5207541,
|
|
||||||
"disposition": "3+kk",
|
|
||||||
"floor": 2,
|
|
||||||
"area": 88,
|
|
||||||
"building_type": "Cihlová",
|
|
||||||
"ownership": "Osobní",
|
|
||||||
"url": "https://www.bezrealitky.cz/nemovitosti-byty-domy/989817-nabidka-prodej-bytu-miroslava-hajna-praha",
|
|
||||||
"source": "bezrealitky",
|
|
||||||
"image": ""
|
|
||||||
},
|
|
||||||
{
|
|
||||||
"hash_id": 970257,
|
|
||||||
"name": "Prodej bytu 3+1 106 m²",
|
|
||||||
"price": 12950000,
|
|
||||||
"price_formatted": "12 950 000 Kč",
|
|
||||||
"locality": "Novákových, Praha - Libeň",
|
|
||||||
"lat": 50.1034771,
|
|
||||||
"lon": 14.4758735,
|
|
||||||
"disposition": "3+1",
|
|
||||||
"floor": 5,
|
|
||||||
"area": 106,
|
|
||||||
"building_type": "Cihlová",
|
|
||||||
"ownership": "Osobní",
|
|
||||||
"url": "https://www.bezrealitky.cz/nemovitosti-byty-domy/970257-nabidka-prodej-bytu-novakovych-praha",
|
|
||||||
"source": "bezrealitky",
|
|
||||||
"image": ""
|
|
||||||
},
|
|
||||||
{
|
|
||||||
"hash_id": 972406,
|
|
||||||
"name": "Prodej bytu 3+kk 83 m²",
|
|
||||||
"price": 10490000,
|
|
||||||
"price_formatted": "10 490 000 Kč",
|
|
||||||
"locality": "Na Výrovně, Praha - Stodůlky",
|
|
||||||
"lat": 50.0396067,
|
|
||||||
"lon": 14.3167022,
|
|
||||||
"disposition": "3+kk",
|
|
||||||
"floor": 2,
|
|
||||||
"area": 83,
|
|
||||||
"building_type": "Cihlová",
|
|
||||||
"ownership": "Osobní",
|
|
||||||
"url": "https://www.bezrealitky.cz/nemovitosti-byty-domy/972406-nabidka-prodej-bytu-na-vyrovne",
|
|
||||||
"source": "bezrealitky",
|
|
||||||
"image": ""
|
|
||||||
},
|
|
||||||
{
|
|
||||||
"hash_id": 967142,
|
|
||||||
"name": "Prodej bytu 3+kk 78 m²",
|
|
||||||
"price": 11648000,
|
|
||||||
"price_formatted": "11 648 000 Kč",
|
|
||||||
"locality": "Na Míčánkách, Praha - Vršovice",
|
|
||||||
"lat": 50.0713284,
|
|
||||||
"lon": 14.4638722,
|
|
||||||
"disposition": "3+kk",
|
|
||||||
"floor": 6,
|
|
||||||
"area": 78,
|
|
||||||
"building_type": "Cihlová",
|
|
||||||
"ownership": "Osobní",
|
|
||||||
"url": "https://www.bezrealitky.cz/nemovitosti-byty-domy/967142-nabidka-prodej-bytu-na-micankach",
|
|
||||||
"source": "bezrealitky",
|
|
||||||
"image": ""
|
|
||||||
},
|
|
||||||
{
|
|
||||||
"hash_id": 955977,
|
|
||||||
"name": "Prodej bytu 4+kk 75 m²",
|
|
||||||
"price": 10363000,
|
|
||||||
"price_formatted": "10 363 000 Kč",
|
|
||||||
"locality": "Karla Guta, Praha - Uhříněves",
|
|
||||||
"lat": 50.03017,
|
|
||||||
"lon": 14.5940072,
|
|
||||||
"disposition": "4+kk",
|
|
||||||
"floor": 4,
|
|
||||||
"area": 75,
|
|
||||||
"building_type": "Cihlová",
|
|
||||||
"ownership": "Osobní",
|
|
||||||
"url": "https://www.bezrealitky.cz/nemovitosti-byty-domy/955977-nabidka-prodej-bytu-karla-guta",
|
|
||||||
"source": "bezrealitky",
|
|
||||||
"image": ""
|
|
||||||
},
|
|
||||||
{
|
|
||||||
"hash_id": 974557,
|
|
||||||
"name": "Prodej bytu 4+kk 94 m²",
|
|
||||||
"price": 13499900,
|
|
||||||
"price_formatted": "13 499 900 Kč",
|
|
||||||
"locality": "V Dolině, Praha - Michle",
|
|
||||||
"lat": 50.0579963,
|
|
||||||
"lon": 14.4682887,
|
|
||||||
"disposition": "4+kk",
|
|
||||||
"floor": 8,
|
|
||||||
"area": 94,
|
|
||||||
"building_type": "Cihlová",
|
|
||||||
"ownership": "Osobní",
|
|
||||||
"url": "https://www.bezrealitky.cz/nemovitosti-byty-domy/974557-nabidka-prodej-bytu-v-doline-praha",
|
|
||||||
"source": "bezrealitky",
|
|
||||||
"image": ""
|
|
||||||
},
|
|
||||||
{
|
|
||||||
"hash_id": 988498,
|
|
||||||
"name": "Prodej bytu 3+1 75 m²",
|
|
||||||
"price": 11400000,
|
|
||||||
"price_formatted": "11 400 000 Kč",
|
|
||||||
"locality": "5. května, Praha - Nusle",
|
|
||||||
"lat": 50.0604096,
|
|
||||||
"lon": 14.4326302,
|
|
||||||
"disposition": "3+1",
|
|
||||||
"floor": 4,
|
|
||||||
"area": 75,
|
|
||||||
"building_type": "Cihlová",
|
|
||||||
"ownership": "Osobní",
|
|
||||||
"url": "https://www.bezrealitky.cz/nemovitosti-byty-domy/988498-nabidka-prodej-bytu-5-kvetna-praha",
|
|
||||||
"source": "bezrealitky",
|
|
||||||
"image": ""
|
|
||||||
},
|
|
||||||
{
|
|
||||||
"hash_id": 985285,
|
|
||||||
"name": "Prodej bytu 3+kk 70 m²",
|
|
||||||
"price": 12200000,
|
|
||||||
"price_formatted": "12 200 000 Kč",
|
|
||||||
"locality": "Klausova, Praha - Stodůlky",
|
|
||||||
"lat": 50.0370204,
|
|
||||||
"lon": 14.3432643,
|
|
||||||
"disposition": "3+kk",
|
|
||||||
"floor": 5,
|
|
||||||
"area": 70,
|
|
||||||
"building_type": "Cihlová",
|
|
||||||
"ownership": "Osobní",
|
|
||||||
"url": "https://www.bezrealitky.cz/nemovitosti-byty-domy/985285-nabidka-prodej-bytu-klausova-praha",
|
|
||||||
"source": "bezrealitky",
|
|
||||||
"image": ""
|
|
||||||
},
|
|
||||||
{
|
|
||||||
"hash_id": 965526,
|
|
||||||
"name": "Prodej bytu 3+kk 77 m²",
|
|
||||||
"price": 11890000,
|
|
||||||
"price_formatted": "11 890 000 Kč",
|
|
||||||
"locality": "Vinohradská, Praha - Strašnice",
|
|
||||||
"lat": 50.0776726,
|
|
||||||
"lon": 14.4870072,
|
|
||||||
"disposition": "3+kk",
|
|
||||||
"floor": 16,
|
|
||||||
"area": 77,
|
|
||||||
"building_type": "Smíšená",
|
|
||||||
"ownership": "Osobní",
|
|
||||||
"url": "https://www.bezrealitky.cz/nemovitosti-byty-domy/965526-nabidka-prodej-bytu-vinohradska-praha",
|
|
||||||
"source": "bezrealitky",
|
|
||||||
"image": ""
|
|
||||||
},
|
|
||||||
{
|
|
||||||
"hash_id": 924811,
|
|
||||||
"name": "Prodej bytu 3+kk 75 m²",
|
|
||||||
"price": 13390000,
|
|
||||||
"price_formatted": "13 390 000 Kč",
|
|
||||||
"locality": "Waltariho, Praha - Hloubětín",
|
|
||||||
"lat": 50.1076717,
|
|
||||||
"lon": 14.5248559,
|
|
||||||
"disposition": "3+kk",
|
|
||||||
"floor": 4,
|
|
||||||
"area": 75,
|
|
||||||
"building_type": "Smíšená",
|
|
||||||
"ownership": "Osobní",
|
|
||||||
"url": "https://www.bezrealitky.cz/nemovitosti-byty-domy/924811-nabidka-prodej-bytu-waltariho-praha",
|
|
||||||
"source": "bezrealitky",
|
|
||||||
"image": ""
|
|
||||||
},
|
|
||||||
{
|
|
||||||
"hash_id": 985859,
|
|
||||||
"name": "Prodej bytu 3+1 80 m²",
|
|
||||||
"price": 9000000,
|
|
||||||
"price_formatted": "9 000 000 Kč",
|
|
||||||
"locality": "Staňkova, Praha - Háje",
|
|
||||||
"lat": 50.0377128,
|
|
||||||
"lon": 14.5311557,
|
|
||||||
"disposition": "3+1",
|
|
||||||
"floor": 2,
|
|
||||||
"area": 80,
|
|
||||||
"building_type": "Cihlová",
|
|
||||||
"ownership": "Osobní",
|
|
||||||
"url": "https://www.bezrealitky.cz/nemovitosti-byty-domy/985859-nabidka-prodej-bytu-stankova-praha",
|
|
||||||
"source": "bezrealitky",
|
|
||||||
"image": ""
|
|
||||||
},
|
|
||||||
{
|
|
||||||
"hash_id": 985583,
|
|
||||||
"name": "Prodej bytu 3+kk 76 m²",
|
|
||||||
"price": 10850000,
|
|
||||||
"price_formatted": "10 850 000 Kč",
|
|
||||||
"locality": "Boloňská, Praha - Horní Měcholupy",
|
|
||||||
"lat": 50.047328,
|
|
||||||
"lon": 14.5565277,
|
|
||||||
"disposition": "3+kk",
|
|
||||||
"floor": 4,
|
|
||||||
"area": 76,
|
|
||||||
"building_type": "Cihlová",
|
|
||||||
"ownership": "Osobní",
|
|
||||||
"url": "https://www.bezrealitky.cz/nemovitosti-byty-domy/985583-nabidka-prodej-bytu-bolonska-praha",
|
|
||||||
"source": "bezrealitky",
|
|
||||||
"image": ""
|
|
||||||
},
|
|
||||||
{
|
|
||||||
"hash_id": 981178,
|
|
||||||
"name": "Prodej bytu 4+kk 86 m²",
|
|
||||||
"price": 11990000,
|
|
||||||
"price_formatted": "11 990 000 Kč",
|
|
||||||
"locality": "Sušilova, Praha - Uhříněves",
|
|
||||||
"lat": 50.032081,
|
|
||||||
"lon": 14.5885148,
|
|
||||||
"disposition": "4+kk",
|
|
||||||
"floor": 2,
|
|
||||||
"area": 86,
|
|
||||||
"building_type": "SKELET",
|
|
||||||
"ownership": "Osobní",
|
|
||||||
"url": "https://www.bezrealitky.cz/nemovitosti-byty-domy/981178-nabidka-prodej-bytu-susilova-praha",
|
|
||||||
"source": "bezrealitky",
|
|
||||||
"image": ""
|
|
||||||
},
|
|
||||||
{
|
|
||||||
"hash_id": 973216,
|
|
||||||
"name": "Prodej bytu 4+1 82 m²",
|
|
||||||
"price": 11357000,
|
|
||||||
"price_formatted": "11 357 000 Kč",
|
|
||||||
"locality": "Nad Kapličkou, Praha - Strašnice",
|
|
||||||
"lat": 50.0839509,
|
|
||||||
"lon": 14.4904493,
|
|
||||||
"disposition": "4+1",
|
|
||||||
"floor": 2,
|
|
||||||
"area": 82,
|
|
||||||
"building_type": "Cihlová",
|
|
||||||
"ownership": "Osobní",
|
|
||||||
"url": "https://www.bezrealitky.cz/nemovitosti-byty-domy/973216-nabidka-prodej-bytu-nad-kaplickou-praha",
|
|
||||||
"source": "bezrealitky",
|
|
||||||
"image": ""
|
|
||||||
},
|
|
||||||
{
|
|
||||||
"hash_id": 868801,
|
|
||||||
"name": "Prodej bytu 3+kk 109 m²",
|
|
||||||
"price": 7299000,
|
|
||||||
"price_formatted": "7 299 000 Kč",
|
|
||||||
"locality": "Pod Karlovem, Praha - Vinohrady",
|
|
||||||
"lat": 50.0676313,
|
|
||||||
"lon": 14.432498,
|
|
||||||
"disposition": "3+kk",
|
|
||||||
"floor": 5,
|
|
||||||
"area": 109,
|
|
||||||
"building_type": "Cihlová",
|
|
||||||
"ownership": "Družstevní",
|
|
||||||
"url": "https://www.bezrealitky.cz/nemovitosti-byty-domy/868801-nabidka-prodej-bytu-pod-karlovem-praha",
|
|
||||||
"source": "bezrealitky",
|
|
||||||
"image": ""
|
|
||||||
},
|
|
||||||
{
|
|
||||||
"hash_id": 868795,
|
|
||||||
"name": "Prodej bytu 3+kk 106 m²",
|
|
||||||
"price": 6299000,
|
|
||||||
"price_formatted": "6 299 000 Kč",
|
|
||||||
"locality": "Pod Karlovem, Praha - Vinohrady",
|
|
||||||
"lat": 50.0676313,
|
|
||||||
"lon": 14.432498,
|
|
||||||
"disposition": "3+kk",
|
|
||||||
"floor": 2,
|
|
||||||
"area": 106,
|
|
||||||
"building_type": "Cihlová",
|
|
||||||
"ownership": "Družstevní",
|
|
||||||
"url": "https://www.bezrealitky.cz/nemovitosti-byty-domy/868795-nabidka-prodej-bytu-pod-karlovem-praha",
|
|
||||||
"source": "bezrealitky",
|
|
||||||
"image": ""
|
|
||||||
},
|
|
||||||
{
|
|
||||||
"hash_id": 981890,
|
|
||||||
"name": "Prodej bytu 3+1 84 m²",
|
|
||||||
"price": 12980000,
|
|
||||||
"price_formatted": "12 980 000 Kč",
|
|
||||||
"locality": "Novákových, Praha - Libeň",
|
|
||||||
"lat": 50.103273,
|
|
||||||
"lon": 14.4746894,
|
|
||||||
"disposition": "3+1",
|
|
||||||
"floor": 2,
|
|
||||||
"area": 84,
|
|
||||||
"building_type": "Cihlová",
|
|
||||||
"ownership": "Osobní",
|
|
||||||
"url": "https://www.bezrealitky.cz/nemovitosti-byty-domy/981890-nabidka-prodej-bytu-novakovych-praha",
|
|
||||||
"source": "bezrealitky",
|
|
||||||
"image": ""
|
|
||||||
},
|
|
||||||
{
|
|
||||||
"hash_id": 976276,
|
|
||||||
"name": "Prodej bytu 3+kk 75 m²",
|
|
||||||
"price": 13490000,
|
|
||||||
"price_formatted": "13 490 000 Kč",
|
|
||||||
"locality": "Svornosti, Praha - Smíchov",
|
|
||||||
"lat": 50.0673284,
|
|
||||||
"lon": 14.4095087,
|
|
||||||
"disposition": "3+kk",
|
|
||||||
"floor": 2,
|
|
||||||
"area": 75,
|
|
||||||
"building_type": "Cihlová",
|
|
||||||
"ownership": "Osobní",
|
|
||||||
"url": "https://www.bezrealitky.cz/nemovitosti-byty-domy/976276-nabidka-prodej-bytu-svornosti-praha",
|
|
||||||
"source": "bezrealitky",
|
|
||||||
"image": ""
|
|
||||||
},
|
|
||||||
{
|
|
||||||
"hash_id": 950787,
|
|
||||||
"name": "Prodej bytu 3+kk 70 m²",
|
|
||||||
"price": 9999000,
|
|
||||||
"price_formatted": "9 999 000 Kč",
|
|
||||||
"locality": "Sečská, Praha - Strašnice",
|
|
||||||
"lat": 50.071191,
|
|
||||||
"lon": 14.5035501,
|
|
||||||
"disposition": "3+kk",
|
|
||||||
"floor": 3,
|
|
||||||
"area": 70,
|
|
||||||
"building_type": "Smíšená",
|
|
||||||
"ownership": "Osobní",
|
|
||||||
"url": "https://www.bezrealitky.cz/nemovitosti-byty-domy/950787-nabidka-prodej-bytu-secska-praha",
|
|
||||||
"source": "bezrealitky",
|
|
||||||
"image": ""
|
|
||||||
},
|
|
||||||
{
|
|
||||||
"hash_id": 978045,
|
|
||||||
"name": "Prodej bytu 3+kk 76 m²",
|
|
||||||
"price": 11133000,
|
|
||||||
"price_formatted": "11 133 000 Kč",
|
|
||||||
"locality": "K Vinoři, Praha - Kbely",
|
|
||||||
"lat": 50.1329656,
|
|
||||||
"lon": 14.5618499,
|
|
||||||
"disposition": "3+kk",
|
|
||||||
"floor": 2,
|
|
||||||
"area": 76,
|
|
||||||
"building_type": "Smíšená",
|
|
||||||
"ownership": "Osobní",
|
|
||||||
"url": "https://www.bezrealitky.cz/nemovitosti-byty-domy/978045-nabidka-prodej-bytu-k-vinori",
|
|
||||||
"source": "bezrealitky",
|
|
||||||
"image": ""
|
|
||||||
},
|
|
||||||
{
|
|
||||||
"hash_id": 974552,
|
|
||||||
"name": "Prodej bytu 3+1 75 m²",
|
|
||||||
"price": 11000000,
|
|
||||||
"price_formatted": "11 000 000 Kč",
|
|
||||||
"locality": "Vejražkova, Praha - Košíře",
|
|
||||||
"lat": 50.0637808,
|
|
||||||
"lon": 14.3612275,
|
|
||||||
"disposition": "3+1",
|
|
||||||
"floor": 2,
|
|
||||||
"area": 75,
|
|
||||||
"building_type": "Cihlová",
|
|
||||||
"ownership": "Osobní",
|
|
||||||
"url": "https://www.bezrealitky.cz/nemovitosti-byty-domy/974552-nabidka-prodej-bytu-vejrazkova-praha",
|
|
||||||
"source": "bezrealitky",
|
|
||||||
"image": ""
|
|
||||||
},
|
|
||||||
{
|
|
||||||
"hash_id": 955010,
|
|
||||||
"name": "Prodej bytu 3+kk 70 m²",
|
|
||||||
"price": 12290000,
|
|
||||||
"price_formatted": "12 290 000 Kč",
|
|
||||||
"locality": "Břeclavská, Praha - Kyje",
|
|
||||||
"lat": 50.0951045,
|
|
||||||
"lon": 14.5454237,
|
|
||||||
"disposition": "3+kk",
|
|
||||||
"floor": 2,
|
|
||||||
"area": 70,
|
|
||||||
"building_type": "Cihlová",
|
|
||||||
"ownership": "Osobní",
|
|
||||||
"url": "https://www.bezrealitky.cz/nemovitosti-byty-domy/955010-nabidka-prodej-bytu-breclavska-hlavni-mesto-praha",
|
|
||||||
"source": "bezrealitky",
|
|
||||||
"image": ""
|
|
||||||
}
|
|
||||||
]
|
|
||||||
@@ -1 +0,0 @@
|
|||||||
[]
|
|
||||||
5867
byty_idnes.json
5867
byty_idnes.json
File diff suppressed because it is too large
Load Diff
12072
byty_merged.json
12072
byty_merged.json
File diff suppressed because it is too large
Load Diff
@@ -1 +0,0 @@
|
|||||||
[]
|
|
||||||
7091
byty_realingo.json
7091
byty_realingo.json
File diff suppressed because it is too large
Load Diff
5570
byty_sreality.json
5570
byty_sreality.json
File diff suppressed because it is too large
Load Diff
123
docs/validation.md
Normal file
123
docs/validation.md
Normal file
@@ -0,0 +1,123 @@
|
|||||||
|
# Validation Recipe
|
||||||
|
|
||||||
|
End-to-end check that scraping, data persistence, history, and the status page all work correctly in Docker.
|
||||||
|
|
||||||
|
## What it verifies
|
||||||
|
|
||||||
|
- All scrapers run and write output to `DATA_DIR` (`/app/data`)
|
||||||
|
- `stats_*.json` land in `/app/data/` (not in `/app/`)
|
||||||
|
- `status.json` and `scraper_history.json` land in `/app/data/`
|
||||||
|
- `/api/status`, `/api/status/history`, and `/scrapers-status` serve correct data
|
||||||
|
- History accumulates across runs
|
||||||
|
|
||||||
|
## Steps
|
||||||
|
|
||||||
|
### 1. Build the image
|
||||||
|
|
||||||
|
```bash
|
||||||
|
make build
|
||||||
|
```
|
||||||
|
|
||||||
|
### 2. Start a clean validation container
|
||||||
|
|
||||||
|
```bash
|
||||||
|
# Stop/remove any leftover container and volume from a previous run
|
||||||
|
docker stop maru-hleda-byt-validation 2>/dev/null; docker rm maru-hleda-byt-validation 2>/dev/null
|
||||||
|
docker volume rm maru-hleda-byt-validation-data 2>/dev/null
|
||||||
|
|
||||||
|
docker run -d --name maru-hleda-byt-validation \
|
||||||
|
-p 8081:8080 \
|
||||||
|
-v maru-hleda-byt-validation-data:/app/data \
|
||||||
|
maru-hleda-byt
|
||||||
|
```
|
||||||
|
|
||||||
|
Give the container ~3 seconds to start. The entrypoint launches a background full scrape automatically — suppress it so only controlled runs execute:
|
||||||
|
|
||||||
|
```bash
|
||||||
|
sleep 3
|
||||||
|
docker exec maru-hleda-byt-validation pkill -f run_all.sh 2>/dev/null || true
|
||||||
|
docker exec maru-hleda-byt-validation rm -f /app/data/scraper_running.json 2>/dev/null || true
|
||||||
|
```
|
||||||
|
|
||||||
|
### 3. Run a limited scrape (run 1)
|
||||||
|
|
||||||
|
```bash
|
||||||
|
docker exec maru-hleda-byt-validation bash /app/run_all.sh --max-pages 1 --max-properties 10
|
||||||
|
```
|
||||||
|
|
||||||
|
Expected output (last few lines):
|
||||||
|
```
|
||||||
|
Status uložen: /app/data/status.json
|
||||||
|
Historie uložena: /app/data/scraper_history.json (1 záznamů)
|
||||||
|
```
|
||||||
|
|
||||||
|
### 4. Verify data files are in `/app/data/`
|
||||||
|
|
||||||
|
```bash
|
||||||
|
docker exec maru-hleda-byt-validation ls /app/data/
|
||||||
|
```
|
||||||
|
|
||||||
|
Expected files:
|
||||||
|
```
|
||||||
|
byty_cityhome.json byty_idnes.json byty_merged.json
|
||||||
|
byty_realingo.json byty_sreality.json
|
||||||
|
mapa_bytu.html
|
||||||
|
scraper_history.json
|
||||||
|
stats_bezrealitky.json stats_cityhome.json stats_idnes.json
|
||||||
|
stats_realingo.json stats_sreality.json
|
||||||
|
status.json
|
||||||
|
```
|
||||||
|
|
||||||
|
### 5. Run a second limited scrape (run 2)
|
||||||
|
|
||||||
|
```bash
|
||||||
|
docker exec maru-hleda-byt-validation bash /app/run_all.sh --max-pages 1 --max-properties 10
|
||||||
|
```
|
||||||
|
|
||||||
|
Expected last line: `Historie uložena: /app/data/scraper_history.json (2 záznamů)`
|
||||||
|
|
||||||
|
### 6. Verify history via API
|
||||||
|
|
||||||
|
```bash
|
||||||
|
curl -s http://localhost:8081/api/status/history | python3 -c "
|
||||||
|
import json, sys
|
||||||
|
h = json.load(sys.stdin)
|
||||||
|
print(f'{len(h)} entries:')
|
||||||
|
for i, e in enumerate(h):
|
||||||
|
print(f' [{i}] {e[\"timestamp\"]} total={e[\"total_accepted\"]}')
|
||||||
|
"
|
||||||
|
```
|
||||||
|
|
||||||
|
Expected: 2 entries with different timestamps.
|
||||||
|
|
||||||
|
```bash
|
||||||
|
curl -s http://localhost:8081/api/status | python3 -c "
|
||||||
|
import json, sys; s=json.load(sys.stdin)
|
||||||
|
print(f'status={s[\"status\"]} total={s[\"total_accepted\"]} ts={s[\"timestamp\"]}')
|
||||||
|
"
|
||||||
|
```
|
||||||
|
|
||||||
|
Expected: `status=done total=<N> ts=<latest timestamp>`
|
||||||
|
|
||||||
|
### 7. Check the status page
|
||||||
|
|
||||||
|
Open http://localhost:8081/scrapers-status in a browser (or `curl -s http://localhost:8081/scrapers-status | grep -c "clickable-row"` — should print `2`).
|
||||||
|
|
||||||
|
### 8. Clean up
|
||||||
|
|
||||||
|
```bash
|
||||||
|
docker stop maru-hleda-byt-validation && docker rm maru-hleda-byt-validation
|
||||||
|
docker volume rm maru-hleda-byt-validation-data
|
||||||
|
```
|
||||||
|
|
||||||
|
Or use the Makefile shortcut:
|
||||||
|
|
||||||
|
```bash
|
||||||
|
make validation-stop
|
||||||
|
```
|
||||||
|
|
||||||
|
## Notes
|
||||||
|
|
||||||
|
- PSN scraper does not support `--max-pages` and will always fail with this command; `success=False` in history is expected during validation.
|
||||||
|
- Bezrealitky may return 0 results with a 1-page limit; `byty_bezrealitky.json` will be absent from `/app/data/` in that case — this is normal.
|
||||||
|
- `make validation` (the Makefile target) runs the same limited scrape but does not suppress the background startup scrape, so two concurrent runs may occur. Use the manual steps above for a clean controlled test.
|
||||||
@@ -1,16 +1,15 @@
|
|||||||
#!/usr/bin/env python3
|
#!/usr/bin/env python3
|
||||||
"""Generate status.json from scraper JSON outputs and run log."""
|
"""Generate status.json from scraper JSON outputs and per-scraper stats files."""
|
||||||
from __future__ import annotations
|
from __future__ import annotations
|
||||||
|
|
||||||
|
import argparse
|
||||||
import json
|
import json
|
||||||
import os
|
import os
|
||||||
import re
|
|
||||||
import sys
|
|
||||||
from datetime import datetime
|
from datetime import datetime
|
||||||
from pathlib import Path
|
from pathlib import Path
|
||||||
from typing import Optional
|
|
||||||
|
|
||||||
HERE = Path(__file__).parent
|
HERE = Path(__file__).parent
|
||||||
|
DATA_DIR = Path(os.environ.get("DATA_DIR", HERE))
|
||||||
|
|
||||||
SOURCE_FILES = {
|
SOURCE_FILES = {
|
||||||
"Sreality": "byty_sreality.json",
|
"Sreality": "byty_sreality.json",
|
||||||
@@ -21,7 +20,17 @@ SOURCE_FILES = {
|
|||||||
"CityHome": "byty_cityhome.json",
|
"CityHome": "byty_cityhome.json",
|
||||||
}
|
}
|
||||||
|
|
||||||
|
STATS_FILES = {
|
||||||
|
"Sreality": "stats_sreality.json",
|
||||||
|
"Realingo": "stats_realingo.json",
|
||||||
|
"Bezrealitky": "stats_bezrealitky.json",
|
||||||
|
"iDNES": "stats_idnes.json",
|
||||||
|
"PSN": "stats_psn.json",
|
||||||
|
"CityHome": "stats_cityhome.json",
|
||||||
|
}
|
||||||
|
|
||||||
MERGED_FILE = "byty_merged.json"
|
MERGED_FILE = "byty_merged.json"
|
||||||
|
HISTORY_FILE = "scraper_history.json"
|
||||||
|
|
||||||
|
|
||||||
def count_source(path: Path) -> dict:
|
def count_source(path: Path) -> dict:
|
||||||
@@ -36,105 +45,51 @@ def count_source(path: Path) -> dict:
|
|||||||
return {"accepted": 0, "error": str(e)}
|
return {"accepted": 0, "error": str(e)}
|
||||||
|
|
||||||
|
|
||||||
def parse_log(log_path: str) -> dict[str, dict]:
|
def read_scraper_stats(path: Path) -> dict:
|
||||||
"""Parse scraper run log and extract per-source statistics.
|
"""Load a per-scraper stats JSON. Returns {} on missing or corrupt file."""
|
||||||
|
if not path.exists():
|
||||||
Scrapers log summary lines like:
|
return {}
|
||||||
✓ Vyhovující byty: 12
|
try:
|
||||||
Vyloučeno (prodáno): 5
|
data = json.loads(path.read_text(encoding="utf-8"))
|
||||||
Staženo stránek: 3
|
return data if isinstance(data, dict) else {}
|
||||||
Staženo inzerátů: 48
|
except Exception:
|
||||||
Celkem bytů v cache: 120
|
|
||||||
and section headers like:
|
|
||||||
[2/6] Realingo
|
|
||||||
"""
|
|
||||||
if not log_path or not os.path.exists(log_path):
|
|
||||||
return {}
|
return {}
|
||||||
|
|
||||||
with open(log_path, encoding="utf-8") as f:
|
|
||||||
content = f.read()
|
|
||||||
|
|
||||||
# Split into per-source sections by the [N/6] Step header
|
def append_to_history(status: dict, keep: int) -> None:
|
||||||
# Each section header looks like "[2/6] Realingo\n----..."
|
"""Append the current status entry to scraper_history.json, keeping only `keep` latest."""
|
||||||
section_pattern = re.compile(r'\[(\d+)/\d+\]\s+(.+)\n-+', re.MULTILINE)
|
history_path = DATA_DIR / HISTORY_FILE
|
||||||
sections_found = list(section_pattern.finditer(content))
|
history: list = []
|
||||||
|
if history_path.exists():
|
||||||
|
try:
|
||||||
|
history = json.loads(history_path.read_text(encoding="utf-8"))
|
||||||
|
if not isinstance(history, list):
|
||||||
|
history = []
|
||||||
|
except Exception:
|
||||||
|
history = []
|
||||||
|
|
||||||
if not sections_found:
|
history.append(status)
|
||||||
return {}
|
|
||||||
|
|
||||||
stats = {}
|
# Keep only the N most recent entries
|
||||||
for i, match in enumerate(sections_found):
|
if keep > 0 and len(history) > keep:
|
||||||
step_name = match.group(2).strip()
|
history = history[-keep:]
|
||||||
start = match.end()
|
|
||||||
end = sections_found[i + 1].start() if i + 1 < len(sections_found) else len(content)
|
|
||||||
section_text = content[start:end]
|
|
||||||
|
|
||||||
# Identify which sources this section covers
|
history_path.write_text(json.dumps(history, ensure_ascii=False, indent=2), encoding="utf-8")
|
||||||
# "PSN + CityHome" covers both
|
print(f"Historie uložena: {history_path} ({len(history)} záznamů)")
|
||||||
source_names = []
|
|
||||||
for name in SOURCE_FILES:
|
|
||||||
if name.lower() in step_name.lower():
|
|
||||||
source_names.append(name)
|
|
||||||
if not source_names:
|
|
||||||
continue
|
|
||||||
|
|
||||||
# Parse numeric summary lines
|
|
||||||
def extract(pattern: str) -> Optional[int]:
|
|
||||||
m = re.search(pattern, section_text)
|
|
||||||
return int(m.group(1)) if m else None
|
|
||||||
|
|
||||||
# Lines present in all/most scrapers
|
|
||||||
accepted = extract(r'Vyhovující byty[:\s]+(\d+)')
|
|
||||||
fetched = extract(r'Staženo inzerátů[:\s]+(\d+)')
|
|
||||||
pages = extract(r'Staženo stránek[:\s]+(\d+)')
|
|
||||||
cached = extract(r'Celkem bytů v cache[:\s]+(\d+)')
|
|
||||||
cache_hits = extract(r'Cache hit[:\s]+(\d+)')
|
|
||||||
|
|
||||||
# Rejection reasons — collect all into a dict
|
|
||||||
excluded = {}
|
|
||||||
for m in re.finditer(r'Vyloučeno\s+\(([^)]+)\)[:\s]+(\d+)', section_text):
|
|
||||||
excluded[m.group(1)] = int(m.group(2))
|
|
||||||
# Also PSN-style "Vyloučeno (prodáno): N"
|
|
||||||
total_excluded = sum(excluded.values()) if excluded else extract(r'Vyloučen\w*[:\s]+(\d+)')
|
|
||||||
|
|
||||||
entry = {}
|
|
||||||
if accepted is not None:
|
|
||||||
entry["accepted"] = accepted
|
|
||||||
if fetched is not None:
|
|
||||||
entry["fetched"] = fetched
|
|
||||||
if pages is not None:
|
|
||||||
entry["pages"] = pages
|
|
||||||
if cached is not None:
|
|
||||||
entry["cached"] = cached
|
|
||||||
if cache_hits is not None:
|
|
||||||
entry["cache_hits"] = cache_hits
|
|
||||||
if excluded:
|
|
||||||
entry["excluded"] = excluded
|
|
||||||
elif total_excluded is not None:
|
|
||||||
entry["excluded_total"] = total_excluded
|
|
||||||
|
|
||||||
for name in source_names:
|
|
||||||
stats[name] = entry
|
|
||||||
|
|
||||||
return stats
|
|
||||||
|
|
||||||
|
|
||||||
def main():
|
def main():
|
||||||
start_time = None
|
parser = argparse.ArgumentParser(description="Generate status.json from scraper outputs.")
|
||||||
duration_sec = None
|
parser.add_argument("--start-time", dest="start_time", default=None,
|
||||||
|
help="ISO timestamp of scrape start (default: now)")
|
||||||
|
parser.add_argument("--duration", dest="duration", type=int, default=None,
|
||||||
|
help="Run duration in seconds")
|
||||||
|
parser.add_argument("--keep", dest="keep", type=int, default=20,
|
||||||
|
help="Number of history entries to keep (default: 20, 0=unlimited)")
|
||||||
|
args = parser.parse_args()
|
||||||
|
|
||||||
if len(sys.argv) >= 3:
|
start_time = args.start_time or datetime.now().isoformat(timespec="seconds")
|
||||||
start_time = sys.argv[1]
|
duration_sec = args.duration
|
||||||
try:
|
|
||||||
duration_sec = int(sys.argv[2])
|
|
||||||
except ValueError:
|
|
||||||
pass
|
|
||||||
|
|
||||||
if not start_time:
|
|
||||||
start_time = datetime.now().isoformat(timespec="seconds")
|
|
||||||
|
|
||||||
log_path = sys.argv[3] if len(sys.argv) >= 4 else None
|
|
||||||
log_stats = parse_log(log_path)
|
|
||||||
|
|
||||||
sources = []
|
sources = []
|
||||||
for name, filename in SOURCE_FILES.items():
|
for name, filename in SOURCE_FILES.items():
|
||||||
@@ -142,14 +97,12 @@ def main():
|
|||||||
info = count_source(path)
|
info = count_source(path)
|
||||||
info["name"] = name
|
info["name"] = name
|
||||||
|
|
||||||
# Merge log stats
|
# Merge in stats from the per-scraper stats file (authoritative for run data)
|
||||||
ls = log_stats.get(name, {})
|
stats = read_scraper_stats(DATA_DIR / STATS_FILES[name])
|
||||||
for k in ("fetched", "pages", "cached", "cache_hits", "excluded", "excluded_total"):
|
for key in ("accepted", "fetched", "pages", "cache_hits", "excluded", "excluded_total",
|
||||||
if k in ls:
|
"success", "duration_sec", "error"):
|
||||||
info[k] = ls[k]
|
if key in stats:
|
||||||
# Override accepted from log if available (log is authoritative for latest run)
|
info[key] = stats[key]
|
||||||
if "accepted" in ls:
|
|
||||||
info["accepted"] = ls["accepted"]
|
|
||||||
|
|
||||||
sources.append(info)
|
sources.append(info)
|
||||||
|
|
||||||
@@ -168,17 +121,21 @@ def main():
|
|||||||
|
|
||||||
duplicates_removed = total_accepted - deduplicated if deduplicated else 0
|
duplicates_removed = total_accepted - deduplicated if deduplicated else 0
|
||||||
|
|
||||||
|
# Top-level success: True if no source has an error
|
||||||
|
success = not any("error" in s for s in sources)
|
||||||
|
|
||||||
status = {
|
status = {
|
||||||
"status": "done",
|
"status": "done",
|
||||||
"timestamp": start_time,
|
"timestamp": start_time,
|
||||||
"duration_sec": duration_sec,
|
"duration_sec": duration_sec,
|
||||||
|
"success": success,
|
||||||
"total_accepted": total_accepted,
|
"total_accepted": total_accepted,
|
||||||
"deduplicated": deduplicated,
|
"deduplicated": deduplicated,
|
||||||
"duplicates_removed": duplicates_removed,
|
"duplicates_removed": duplicates_removed,
|
||||||
"sources": sources,
|
"sources": sources,
|
||||||
}
|
}
|
||||||
|
|
||||||
out = HERE / "status.json"
|
out = DATA_DIR / "status.json"
|
||||||
out.write_text(json.dumps(status, ensure_ascii=False, indent=2), encoding="utf-8")
|
out.write_text(json.dumps(status, ensure_ascii=False, indent=2), encoding="utf-8")
|
||||||
print(f"Status uložen: {out}")
|
print(f"Status uložen: {out}")
|
||||||
print(f" Celkem bytů (před dedup): {total_accepted}")
|
print(f" Celkem bytů (před dedup): {total_accepted}")
|
||||||
@@ -197,6 +154,8 @@ def main():
|
|||||||
parts.append(f"[CHYBA: {err}]")
|
parts.append(f"[CHYBA: {err}]")
|
||||||
print(" " + " ".join(parts))
|
print(" " + " ".join(parts))
|
||||||
|
|
||||||
|
append_to_history(status, args.keep)
|
||||||
|
|
||||||
|
|
||||||
if __name__ == "__main__":
|
if __name__ == "__main__":
|
||||||
main()
|
main()
|
||||||
|
|||||||
1245
mapa_bytu.html
1245
mapa_bytu.html
File diff suppressed because it is too large
Load Diff
@@ -1,116 +0,0 @@
|
|||||||
#!/usr/bin/env python3
|
|
||||||
"""
|
|
||||||
Minimal HTTP API server for persisting apartment ratings.
|
|
||||||
|
|
||||||
GET /api/ratings → returns ratings.json contents
|
|
||||||
POST /api/ratings → saves entire ratings object
|
|
||||||
GET /api/ratings/export → same as GET, but with download header
|
|
||||||
|
|
||||||
Ratings file: /app/data/ratings.json (or ./ratings.json locally)
|
|
||||||
"""
|
|
||||||
|
|
||||||
import json
|
|
||||||
import logging
|
|
||||||
import os
|
|
||||||
import sys
|
|
||||||
from http.server import BaseHTTPRequestHandler, HTTPServer
|
|
||||||
from pathlib import Path
|
|
||||||
|
|
||||||
PORT = int(os.environ.get("RATINGS_PORT", 8081))
|
|
||||||
DATA_DIR = Path(os.environ.get("DATA_DIR", "."))
|
|
||||||
RATINGS_FILE = DATA_DIR / "ratings.json"
|
|
||||||
|
|
||||||
logging.basicConfig(
|
|
||||||
level=logging.INFO,
|
|
||||||
format="%(asctime)s [ratings] %(levelname)s %(message)s",
|
|
||||||
datefmt="%Y-%m-%dT%H:%M:%S",
|
|
||||||
)
|
|
||||||
log = logging.getLogger(__name__)
|
|
||||||
|
|
||||||
|
|
||||||
def load_ratings() -> dict:
|
|
||||||
try:
|
|
||||||
if RATINGS_FILE.exists():
|
|
||||||
return json.loads(RATINGS_FILE.read_text(encoding="utf-8"))
|
|
||||||
except Exception as e:
|
|
||||||
log.error("Failed to load ratings: %s", e)
|
|
||||||
return {}
|
|
||||||
|
|
||||||
|
|
||||||
def save_ratings(data: dict) -> None:
|
|
||||||
RATINGS_FILE.write_text(
|
|
||||||
json.dumps(data, ensure_ascii=False, indent=2),
|
|
||||||
encoding="utf-8",
|
|
||||||
)
|
|
||||||
|
|
||||||
|
|
||||||
class RatingsHandler(BaseHTTPRequestHandler):
|
|
||||||
def log_message(self, format, *args):
|
|
||||||
# Suppress default HTTP access log (we use our own)
|
|
||||||
pass
|
|
||||||
|
|
||||||
def _send_json(self, status: int, body: dict, extra_headers=None):
|
|
||||||
payload = json.dumps(body, ensure_ascii=False).encode("utf-8")
|
|
||||||
self.send_response(status)
|
|
||||||
self.send_header("Content-Type", "application/json; charset=utf-8")
|
|
||||||
self.send_header("Content-Length", str(len(payload)))
|
|
||||||
self.send_header("Access-Control-Allow-Origin", "*")
|
|
||||||
self.send_header("Access-Control-Allow-Methods", "GET, POST, OPTIONS")
|
|
||||||
self.send_header("Access-Control-Allow-Headers", "Content-Type")
|
|
||||||
if extra_headers:
|
|
||||||
for k, v in extra_headers.items():
|
|
||||||
self.send_header(k, v)
|
|
||||||
self.end_headers()
|
|
||||||
self.wfile.write(payload)
|
|
||||||
|
|
||||||
def do_OPTIONS(self):
|
|
||||||
# CORS preflight
|
|
||||||
self.send_response(204)
|
|
||||||
self.send_header("Access-Control-Allow-Origin", "*")
|
|
||||||
self.send_header("Access-Control-Allow-Methods", "GET, POST, OPTIONS")
|
|
||||||
self.send_header("Access-Control-Allow-Headers", "Content-Type")
|
|
||||||
self.end_headers()
|
|
||||||
|
|
||||||
def do_GET(self):
|
|
||||||
if self.path in ("/api/ratings", "/api/ratings/export"):
|
|
||||||
ratings = load_ratings()
|
|
||||||
extra = None
|
|
||||||
if self.path == "/api/ratings/export":
|
|
||||||
extra = {"Content-Disposition": 'attachment; filename="ratings.json"'}
|
|
||||||
log.info("GET %s → %d ratings", self.path, len(ratings))
|
|
||||||
self._send_json(200, ratings, extra)
|
|
||||||
else:
|
|
||||||
self._send_json(404, {"error": "not found"})
|
|
||||||
|
|
||||||
def do_POST(self):
|
|
||||||
if self.path == "/api/ratings":
|
|
||||||
length = int(self.headers.get("Content-Length", 0))
|
|
||||||
if length == 0:
|
|
||||||
self._send_json(400, {"error": "empty body"})
|
|
||||||
return
|
|
||||||
try:
|
|
||||||
raw = self.rfile.read(length)
|
|
||||||
data = json.loads(raw.decode("utf-8"))
|
|
||||||
except Exception as e:
|
|
||||||
log.warning("Bad request body: %s", e)
|
|
||||||
self._send_json(400, {"error": "invalid JSON"})
|
|
||||||
return
|
|
||||||
if not isinstance(data, dict):
|
|
||||||
self._send_json(400, {"error": "expected JSON object"})
|
|
||||||
return
|
|
||||||
save_ratings(data)
|
|
||||||
log.info("POST /api/ratings → saved %d ratings", len(data))
|
|
||||||
self._send_json(200, {"ok": True, "count": len(data)})
|
|
||||||
else:
|
|
||||||
self._send_json(404, {"error": "not found"})
|
|
||||||
|
|
||||||
|
|
||||||
if __name__ == "__main__":
|
|
||||||
log.info("Ratings server starting on port %d, data dir: %s", PORT, DATA_DIR)
|
|
||||||
log.info("Ratings file: %s", RATINGS_FILE)
|
|
||||||
server = HTTPServer(("0.0.0.0", PORT), RatingsHandler)
|
|
||||||
try:
|
|
||||||
server.serve_forever()
|
|
||||||
except KeyboardInterrupt:
|
|
||||||
log.info("Stopped.")
|
|
||||||
sys.exit(0)
|
|
||||||
15
run_all.sh
15
run_all.sh
@@ -20,8 +20,10 @@ START_TIME=$(date -u +"%Y-%m-%dT%H:%M:%S")
|
|||||||
START_EPOCH=$(date +%s)
|
START_EPOCH=$(date +%s)
|
||||||
LOG_FILE="$(pwd)/scrape_run.log"
|
LOG_FILE="$(pwd)/scrape_run.log"
|
||||||
|
|
||||||
# Mark status as running
|
# Mark scraper as running; cleaned up on exit (even on error/kill)
|
||||||
echo '{"status":"running"}' > status.json
|
LOCK_FILE="${DATA_DIR:-.}/scraper_running.json"
|
||||||
|
echo '{"running":true,"started_at":"'"$START_TIME"'"}' > "$LOCK_FILE"
|
||||||
|
trap 'rm -f "$LOCK_FILE"' EXIT
|
||||||
|
|
||||||
show_help() {
|
show_help() {
|
||||||
echo "Usage: ./run_all.sh [OPTIONS]"
|
echo "Usage: ./run_all.sh [OPTIONS]"
|
||||||
@@ -32,16 +34,19 @@ show_help() {
|
|||||||
echo " --max-pages N Maximální počet stránek ke stažení z každého zdroje"
|
echo " --max-pages N Maximální počet stránek ke stažení z každého zdroje"
|
||||||
echo " --max-properties N Maximální počet nemovitostí ke stažení z každého zdroje"
|
echo " --max-properties N Maximální počet nemovitostí ke stažení z každého zdroje"
|
||||||
echo " --log-level LEVEL Úroveň logování (DEBUG, INFO, WARNING, ERROR)"
|
echo " --log-level LEVEL Úroveň logování (DEBUG, INFO, WARNING, ERROR)"
|
||||||
|
echo " --keep N Počet běhů v historii (výchozí: 5, 0=neomezeno)"
|
||||||
echo " -h, --help Zobrazí tuto nápovědu"
|
echo " -h, --help Zobrazí tuto nápovědu"
|
||||||
echo ""
|
echo ""
|
||||||
echo "Examples:"
|
echo "Examples:"
|
||||||
echo " ./run_all.sh # plný běh"
|
echo " ./run_all.sh # plný běh"
|
||||||
echo " ./run_all.sh --max-pages 1 --max-properties 10 # rychlý test"
|
echo " ./run_all.sh --max-pages 1 --max-properties 10 # rychlý test"
|
||||||
echo " ./run_all.sh --log-level DEBUG # s debug logováním"
|
echo " ./run_all.sh --log-level DEBUG # s debug logováním"
|
||||||
|
echo " ./run_all.sh --keep 10 # uchovej 10 běhů v historii"
|
||||||
}
|
}
|
||||||
|
|
||||||
# Parse arguments
|
# Parse arguments
|
||||||
SCRAPER_ARGS=""
|
SCRAPER_ARGS=""
|
||||||
|
KEEP_ARG=""
|
||||||
while [[ $# -gt 0 ]]; do
|
while [[ $# -gt 0 ]]; do
|
||||||
case $1 in
|
case $1 in
|
||||||
-h|--help)
|
-h|--help)
|
||||||
@@ -52,6 +57,10 @@ while [[ $# -gt 0 ]]; do
|
|||||||
SCRAPER_ARGS="$SCRAPER_ARGS $1 $2"
|
SCRAPER_ARGS="$SCRAPER_ARGS $1 $2"
|
||||||
shift 2
|
shift 2
|
||||||
;;
|
;;
|
||||||
|
--keep)
|
||||||
|
KEEP_ARG="--keep $2"
|
||||||
|
shift 2
|
||||||
|
;;
|
||||||
*)
|
*)
|
||||||
echo "Unknown argument: $1"
|
echo "Unknown argument: $1"
|
||||||
echo ""
|
echo ""
|
||||||
@@ -103,7 +112,7 @@ python3 merge_and_map.py || { echo -e "${RED}✗ Merge selhal${NC}"; FAILED=$((F
|
|||||||
|
|
||||||
END_EPOCH=$(date +%s)
|
END_EPOCH=$(date +%s)
|
||||||
DURATION=$((END_EPOCH - START_EPOCH))
|
DURATION=$((END_EPOCH - START_EPOCH))
|
||||||
python3 generate_status.py "$START_TIME" "$DURATION" "$LOG_FILE"
|
python3 generate_status.py --start-time "$START_TIME" --duration "$DURATION" $KEEP_ARG
|
||||||
|
|
||||||
echo ""
|
echo ""
|
||||||
echo "============================================================"
|
echo "============================================================"
|
||||||
|
|||||||
@@ -15,6 +15,9 @@ import urllib.request
|
|||||||
import urllib.parse
|
import urllib.parse
|
||||||
from datetime import datetime
|
from datetime import datetime
|
||||||
from pathlib import Path
|
from pathlib import Path
|
||||||
|
from scraper_stats import write_stats
|
||||||
|
|
||||||
|
STATS_FILE = "stats_sreality.json"
|
||||||
|
|
||||||
logger = logging.getLogger(__name__)
|
logger = logging.getLogger(__name__)
|
||||||
|
|
||||||
@@ -209,6 +212,8 @@ def load_cache(json_path: str = "byty_sreality.json") -> dict[int, dict]:
|
|||||||
|
|
||||||
def scrape(max_pages: int | None = None, max_properties: int | None = None):
|
def scrape(max_pages: int | None = None, max_properties: int | None = None):
|
||||||
"""Main scraping function. Returns list of filtered estates."""
|
"""Main scraping function. Returns list of filtered estates."""
|
||||||
|
_run_start = time.time()
|
||||||
|
_run_ts = datetime.now().isoformat(timespec="seconds")
|
||||||
all_estates_raw = []
|
all_estates_raw = []
|
||||||
cache = load_cache()
|
cache = load_cache()
|
||||||
|
|
||||||
@@ -366,6 +371,21 @@ def scrape(max_pages: int | None = None, max_properties: int | None = None):
|
|||||||
logger.info(f" ✓ Vyhovující byty: {len(results)}")
|
logger.info(f" ✓ Vyhovující byty: {len(results)}")
|
||||||
logger.info(f"{'=' * 60}")
|
logger.info(f"{'=' * 60}")
|
||||||
|
|
||||||
|
write_stats(STATS_FILE, {
|
||||||
|
"source": "Sreality",
|
||||||
|
"timestamp": _run_ts,
|
||||||
|
"duration_sec": round(time.time() - _run_start, 1),
|
||||||
|
"success": True,
|
||||||
|
"accepted": len(results),
|
||||||
|
"fetched": len(unique_estates),
|
||||||
|
"cache_hits": cache_hits,
|
||||||
|
"excluded": {
|
||||||
|
"panel/síd": excluded_panel,
|
||||||
|
"<69 m²": excluded_small,
|
||||||
|
"bez GPS": excluded_no_gps,
|
||||||
|
"bez detailu": excluded_no_detail,
|
||||||
|
},
|
||||||
|
})
|
||||||
return results
|
return results
|
||||||
|
|
||||||
|
|
||||||
@@ -653,7 +673,7 @@ def generate_map(estates: list[dict], output_path: str = "mapa_bytu.html"):
|
|||||||
Skrýt zamítnuté
|
Skrýt zamítnuté
|
||||||
</label>
|
</label>
|
||||||
</div>
|
</div>
|
||||||
<div class="status-link"><a href="status.html">Scraper status</a></div>
|
<div class="status-link"><a href="/scrapers-status">Scraper status</a></div>
|
||||||
</div>
|
</div>
|
||||||
|
|
||||||
<script>
|
<script>
|
||||||
@@ -1089,8 +1109,22 @@ if __name__ == "__main__":
|
|||||||
handlers=[logging.StreamHandler()]
|
handlers=[logging.StreamHandler()]
|
||||||
)
|
)
|
||||||
|
|
||||||
|
_run_ts = datetime.now().isoformat(timespec="seconds")
|
||||||
start = time.time()
|
start = time.time()
|
||||||
|
try:
|
||||||
estates = scrape(max_pages=args.max_pages, max_properties=args.max_properties)
|
estates = scrape(max_pages=args.max_pages, max_properties=args.max_properties)
|
||||||
|
except Exception as e:
|
||||||
|
logger.error(f"Scraper failed: {e}", exc_info=True)
|
||||||
|
write_stats(STATS_FILE, {
|
||||||
|
"source": "Sreality",
|
||||||
|
"timestamp": _run_ts,
|
||||||
|
"duration_sec": round(time.time() - start, 1),
|
||||||
|
"success": False,
|
||||||
|
"accepted": 0,
|
||||||
|
"fetched": 0,
|
||||||
|
"error": str(e),
|
||||||
|
})
|
||||||
|
raise
|
||||||
|
|
||||||
if estates:
|
if estates:
|
||||||
# Save raw data as JSON backup
|
# Save raw data as JSON backup
|
||||||
|
|||||||
@@ -15,6 +15,9 @@ import re
|
|||||||
import time
|
import time
|
||||||
import urllib.request
|
import urllib.request
|
||||||
from pathlib import Path
|
from pathlib import Path
|
||||||
|
from scraper_stats import write_stats
|
||||||
|
|
||||||
|
STATS_FILE = "stats_bezrealitky.json"
|
||||||
|
|
||||||
logger = logging.getLogger(__name__)
|
logger = logging.getLogger(__name__)
|
||||||
|
|
||||||
@@ -171,6 +174,8 @@ def load_cache(json_path: str = "byty_bezrealitky.json") -> dict[int, dict]:
|
|||||||
|
|
||||||
|
|
||||||
def scrape(max_pages: int | None = None, max_properties: int | None = None):
|
def scrape(max_pages: int | None = None, max_properties: int | None = None):
|
||||||
|
_run_start = time.time()
|
||||||
|
_run_ts = datetime.now().isoformat(timespec="seconds")
|
||||||
cache = load_cache()
|
cache = load_cache()
|
||||||
|
|
||||||
logger.info("=" * 60)
|
logger.info("=" * 60)
|
||||||
@@ -374,6 +379,25 @@ def scrape(max_pages: int | None = None, max_properties: int | None = None):
|
|||||||
logger.info(f" ✓ Vyhovující byty: {len(results)}")
|
logger.info(f" ✓ Vyhovující byty: {len(results)}")
|
||||||
logger.info(f"{'=' * 60}")
|
logger.info(f"{'=' * 60}")
|
||||||
|
|
||||||
|
write_stats(STATS_FILE, {
|
||||||
|
"source": "Bezrealitky",
|
||||||
|
"timestamp": _run_ts,
|
||||||
|
"duration_sec": round(time.time() - _run_start, 1),
|
||||||
|
"success": True,
|
||||||
|
"accepted": len(results),
|
||||||
|
"fetched": len(all_adverts),
|
||||||
|
"pages": page - 1,
|
||||||
|
"cache_hits": cache_hits,
|
||||||
|
"excluded": {
|
||||||
|
"dispozice": excluded_disp,
|
||||||
|
"cena": excluded_price,
|
||||||
|
"plocha": excluded_area,
|
||||||
|
"bez GPS": excluded_no_gps,
|
||||||
|
"panel/síd": excluded_panel,
|
||||||
|
"patro": excluded_floor,
|
||||||
|
"bez detailu": excluded_detail,
|
||||||
|
},
|
||||||
|
})
|
||||||
return results
|
return results
|
||||||
|
|
||||||
|
|
||||||
@@ -394,8 +418,22 @@ if __name__ == "__main__":
|
|||||||
handlers=[logging.StreamHandler()]
|
handlers=[logging.StreamHandler()]
|
||||||
)
|
)
|
||||||
|
|
||||||
|
_run_ts = datetime.now().isoformat(timespec="seconds")
|
||||||
start = time.time()
|
start = time.time()
|
||||||
|
try:
|
||||||
estates = scrape(max_pages=args.max_pages, max_properties=args.max_properties)
|
estates = scrape(max_pages=args.max_pages, max_properties=args.max_properties)
|
||||||
|
except Exception as e:
|
||||||
|
logger.error(f"Scraper failed: {e}", exc_info=True)
|
||||||
|
write_stats(STATS_FILE, {
|
||||||
|
"source": "Bezrealitky",
|
||||||
|
"timestamp": _run_ts,
|
||||||
|
"duration_sec": round(time.time() - start, 1),
|
||||||
|
"success": False,
|
||||||
|
"accepted": 0,
|
||||||
|
"fetched": 0,
|
||||||
|
"error": str(e),
|
||||||
|
})
|
||||||
|
raise
|
||||||
|
|
||||||
if estates:
|
if estates:
|
||||||
json_path = Path("byty_bezrealitky.json")
|
json_path = Path("byty_bezrealitky.json")
|
||||||
|
|||||||
@@ -14,6 +14,9 @@ import time
|
|||||||
import urllib.request
|
import urllib.request
|
||||||
from datetime import datetime
|
from datetime import datetime
|
||||||
from pathlib import Path
|
from pathlib import Path
|
||||||
|
from scraper_stats import write_stats
|
||||||
|
|
||||||
|
STATS_FILE = "stats_cityhome.json"
|
||||||
|
|
||||||
logger = logging.getLogger(__name__)
|
logger = logging.getLogger(__name__)
|
||||||
|
|
||||||
@@ -203,6 +206,8 @@ def extract_project_gps(html: str) -> tuple[float, float] | None:
|
|||||||
|
|
||||||
|
|
||||||
def scrape(max_pages: int | None = None, max_properties: int | None = None):
|
def scrape(max_pages: int | None = None, max_properties: int | None = None):
|
||||||
|
_run_start = time.time()
|
||||||
|
_run_ts = datetime.now().isoformat(timespec="seconds")
|
||||||
logger.info("=" * 60)
|
logger.info("=" * 60)
|
||||||
logger.info("Stahuji inzeráty z CityHome (city-home.cz)")
|
logger.info("Stahuji inzeráty z CityHome (city-home.cz)")
|
||||||
logger.info(f"Cena: do {format_price(MAX_PRICE)}")
|
logger.info(f"Cena: do {format_price(MAX_PRICE)}")
|
||||||
@@ -374,6 +379,23 @@ def scrape(max_pages: int | None = None, max_properties: int | None = None):
|
|||||||
logger.info(f" ✓ Vyhovující byty: {len(results)}")
|
logger.info(f" ✓ Vyhovující byty: {len(results)}")
|
||||||
logger.info(f"{'=' * 60}")
|
logger.info(f"{'=' * 60}")
|
||||||
|
|
||||||
|
write_stats(STATS_FILE, {
|
||||||
|
"source": "CityHome",
|
||||||
|
"timestamp": _run_ts,
|
||||||
|
"duration_sec": round(time.time() - _run_start, 1),
|
||||||
|
"success": True,
|
||||||
|
"accepted": len(results),
|
||||||
|
"fetched": len(all_listings),
|
||||||
|
"excluded": {
|
||||||
|
"prodáno": excluded_sold,
|
||||||
|
"typ": excluded_type,
|
||||||
|
"dispozice": excluded_disp,
|
||||||
|
"cena": excluded_price,
|
||||||
|
"plocha": excluded_area,
|
||||||
|
"patro": excluded_floor,
|
||||||
|
"bez GPS": excluded_no_gps,
|
||||||
|
},
|
||||||
|
})
|
||||||
return results
|
return results
|
||||||
|
|
||||||
|
|
||||||
@@ -394,8 +416,22 @@ if __name__ == "__main__":
|
|||||||
handlers=[logging.StreamHandler()]
|
handlers=[logging.StreamHandler()]
|
||||||
)
|
)
|
||||||
|
|
||||||
|
_run_ts = datetime.now().isoformat(timespec="seconds")
|
||||||
start = time.time()
|
start = time.time()
|
||||||
|
try:
|
||||||
estates = scrape(max_pages=args.max_pages, max_properties=args.max_properties)
|
estates = scrape(max_pages=args.max_pages, max_properties=args.max_properties)
|
||||||
|
except Exception as e:
|
||||||
|
logger.error(f"Scraper failed: {e}", exc_info=True)
|
||||||
|
write_stats(STATS_FILE, {
|
||||||
|
"source": "CityHome",
|
||||||
|
"timestamp": _run_ts,
|
||||||
|
"duration_sec": round(time.time() - start, 1),
|
||||||
|
"success": False,
|
||||||
|
"accepted": 0,
|
||||||
|
"fetched": 0,
|
||||||
|
"error": str(e),
|
||||||
|
})
|
||||||
|
raise
|
||||||
|
|
||||||
if estates:
|
if estates:
|
||||||
json_path = Path("byty_cityhome.json")
|
json_path = Path("byty_cityhome.json")
|
||||||
|
|||||||
@@ -17,6 +17,9 @@ import urllib.request
|
|||||||
import urllib.parse
|
import urllib.parse
|
||||||
from html.parser import HTMLParser
|
from html.parser import HTMLParser
|
||||||
from pathlib import Path
|
from pathlib import Path
|
||||||
|
from scraper_stats import write_stats
|
||||||
|
|
||||||
|
STATS_FILE = "stats_idnes.json"
|
||||||
|
|
||||||
logger = logging.getLogger(__name__)
|
logger = logging.getLogger(__name__)
|
||||||
|
|
||||||
@@ -279,6 +282,8 @@ def load_cache(json_path: str = "byty_idnes.json") -> dict[str, dict]:
|
|||||||
|
|
||||||
|
|
||||||
def scrape(max_pages: int | None = None, max_properties: int | None = None):
|
def scrape(max_pages: int | None = None, max_properties: int | None = None):
|
||||||
|
_run_start = time.time()
|
||||||
|
_run_ts = datetime.now().isoformat(timespec="seconds")
|
||||||
cache = load_cache()
|
cache = load_cache()
|
||||||
|
|
||||||
logger.info("=" * 60)
|
logger.info("=" * 60)
|
||||||
@@ -478,6 +483,25 @@ def scrape(max_pages: int | None = None, max_properties: int | None = None):
|
|||||||
logger.info(f" ✓ Vyhovující byty: {len(results)}")
|
logger.info(f" ✓ Vyhovující byty: {len(results)}")
|
||||||
logger.info(f"{'=' * 60}")
|
logger.info(f"{'=' * 60}")
|
||||||
|
|
||||||
|
write_stats(STATS_FILE, {
|
||||||
|
"source": "iDNES",
|
||||||
|
"timestamp": _run_ts,
|
||||||
|
"duration_sec": round(time.time() - _run_start, 1),
|
||||||
|
"success": True,
|
||||||
|
"accepted": len(results),
|
||||||
|
"fetched": len(all_listings),
|
||||||
|
"pages": page,
|
||||||
|
"cache_hits": cache_hits,
|
||||||
|
"excluded": {
|
||||||
|
"cena": excluded_price,
|
||||||
|
"plocha": excluded_area,
|
||||||
|
"dispozice": excluded_disp,
|
||||||
|
"panel/síd": excluded_panel,
|
||||||
|
"patro": excluded_floor,
|
||||||
|
"bez GPS": excluded_no_gps,
|
||||||
|
"bez detailu": excluded_detail,
|
||||||
|
},
|
||||||
|
})
|
||||||
return results
|
return results
|
||||||
|
|
||||||
|
|
||||||
@@ -498,8 +522,22 @@ if __name__ == "__main__":
|
|||||||
handlers=[logging.StreamHandler()]
|
handlers=[logging.StreamHandler()]
|
||||||
)
|
)
|
||||||
|
|
||||||
|
_run_ts = datetime.now().isoformat(timespec="seconds")
|
||||||
start = time.time()
|
start = time.time()
|
||||||
|
try:
|
||||||
estates = scrape(max_pages=args.max_pages, max_properties=args.max_properties)
|
estates = scrape(max_pages=args.max_pages, max_properties=args.max_properties)
|
||||||
|
except Exception as e:
|
||||||
|
logger.error(f"Scraper failed: {e}", exc_info=True)
|
||||||
|
write_stats(STATS_FILE, {
|
||||||
|
"source": "iDNES",
|
||||||
|
"timestamp": _run_ts,
|
||||||
|
"duration_sec": round(time.time() - start, 1),
|
||||||
|
"success": False,
|
||||||
|
"accepted": 0,
|
||||||
|
"fetched": 0,
|
||||||
|
"error": str(e),
|
||||||
|
})
|
||||||
|
raise
|
||||||
|
|
||||||
if estates:
|
if estates:
|
||||||
json_path = Path("byty_idnes.json")
|
json_path = Path("byty_idnes.json")
|
||||||
|
|||||||
@@ -15,6 +15,9 @@ import time
|
|||||||
from datetime import datetime
|
from datetime import datetime
|
||||||
from pathlib import Path
|
from pathlib import Path
|
||||||
from urllib.parse import urlencode
|
from urllib.parse import urlencode
|
||||||
|
from scraper_stats import write_stats
|
||||||
|
|
||||||
|
STATS_FILE = "stats_psn.json"
|
||||||
|
|
||||||
logger = logging.getLogger(__name__)
|
logger = logging.getLogger(__name__)
|
||||||
|
|
||||||
@@ -67,6 +70,8 @@ def format_price(price: int) -> str:
|
|||||||
|
|
||||||
|
|
||||||
def scrape(max_properties: int | None = None):
|
def scrape(max_properties: int | None = None):
|
||||||
|
_run_start = time.time()
|
||||||
|
_run_ts = datetime.now().isoformat(timespec="seconds")
|
||||||
logger.info("=" * 60)
|
logger.info("=" * 60)
|
||||||
logger.info("Stahuji inzeráty z PSN.cz")
|
logger.info("Stahuji inzeráty z PSN.cz")
|
||||||
logger.info(f"Cena: do {format_price(MAX_PRICE)}")
|
logger.info(f"Cena: do {format_price(MAX_PRICE)}")
|
||||||
@@ -93,6 +98,15 @@ def scrape(max_properties: int | None = None):
|
|||||||
data = fetch_json(url)
|
data = fetch_json(url)
|
||||||
except Exception as e:
|
except Exception as e:
|
||||||
logger.error(f"Chyba při stahování: {e}", exc_info=True)
|
logger.error(f"Chyba při stahování: {e}", exc_info=True)
|
||||||
|
write_stats(STATS_FILE, {
|
||||||
|
"source": "PSN",
|
||||||
|
"timestamp": _run_ts,
|
||||||
|
"duration_sec": round(time.time() - _run_start, 1),
|
||||||
|
"success": False,
|
||||||
|
"accepted": 0,
|
||||||
|
"fetched": 0,
|
||||||
|
"error": str(e),
|
||||||
|
})
|
||||||
return []
|
return []
|
||||||
|
|
||||||
all_units = data.get("units", {}).get("data", [])
|
all_units = data.get("units", {}).get("data", [])
|
||||||
@@ -241,6 +255,15 @@ def scrape(max_properties: int | None = None):
|
|||||||
logger.info(f" ✓ Vyhovující byty: {len(results)}")
|
logger.info(f" ✓ Vyhovující byty: {len(results)}")
|
||||||
logger.info(f"{'=' * 60}")
|
logger.info(f"{'=' * 60}")
|
||||||
|
|
||||||
|
write_stats(STATS_FILE, {
|
||||||
|
"source": "PSN",
|
||||||
|
"timestamp": _run_ts,
|
||||||
|
"duration_sec": round(time.time() - _run_start, 1),
|
||||||
|
"success": True,
|
||||||
|
"accepted": len(results),
|
||||||
|
"fetched": len(all_units),
|
||||||
|
"excluded": excluded,
|
||||||
|
})
|
||||||
return results
|
return results
|
||||||
|
|
||||||
|
|
||||||
@@ -259,8 +282,22 @@ if __name__ == "__main__":
|
|||||||
handlers=[logging.StreamHandler()]
|
handlers=[logging.StreamHandler()]
|
||||||
)
|
)
|
||||||
|
|
||||||
|
_run_ts = datetime.now().isoformat(timespec="seconds")
|
||||||
start = time.time()
|
start = time.time()
|
||||||
|
try:
|
||||||
estates = scrape(max_properties=args.max_properties)
|
estates = scrape(max_properties=args.max_properties)
|
||||||
|
except Exception as e:
|
||||||
|
logger.error(f"Scraper failed: {e}", exc_info=True)
|
||||||
|
write_stats(STATS_FILE, {
|
||||||
|
"source": "PSN",
|
||||||
|
"timestamp": _run_ts,
|
||||||
|
"duration_sec": round(time.time() - start, 1),
|
||||||
|
"success": False,
|
||||||
|
"accepted": 0,
|
||||||
|
"fetched": 0,
|
||||||
|
"error": str(e),
|
||||||
|
})
|
||||||
|
raise
|
||||||
|
|
||||||
if estates:
|
if estates:
|
||||||
json_path = Path("byty_psn.json")
|
json_path = Path("byty_psn.json")
|
||||||
|
|||||||
@@ -15,6 +15,9 @@ import re
|
|||||||
import time
|
import time
|
||||||
import urllib.request
|
import urllib.request
|
||||||
from pathlib import Path
|
from pathlib import Path
|
||||||
|
from scraper_stats import write_stats
|
||||||
|
|
||||||
|
STATS_FILE = "stats_realingo.json"
|
||||||
|
|
||||||
logger = logging.getLogger(__name__)
|
logger = logging.getLogger(__name__)
|
||||||
|
|
||||||
@@ -136,6 +139,8 @@ def load_cache(json_path: str = "byty_realingo.json") -> dict[int, dict]:
|
|||||||
|
|
||||||
|
|
||||||
def scrape(max_pages: int | None = None, max_properties: int | None = None):
|
def scrape(max_pages: int | None = None, max_properties: int | None = None):
|
||||||
|
_run_start = time.time()
|
||||||
|
_run_ts = datetime.now().isoformat(timespec="seconds")
|
||||||
cache = load_cache()
|
cache = load_cache()
|
||||||
|
|
||||||
logger.info("=" * 60)
|
logger.info("=" * 60)
|
||||||
@@ -333,6 +338,25 @@ def scrape(max_pages: int | None = None, max_properties: int | None = None):
|
|||||||
logger.info(f" ✓ Vyhovující byty: {len(results)}")
|
logger.info(f" ✓ Vyhovující byty: {len(results)}")
|
||||||
logger.info(f"{'=' * 60}")
|
logger.info(f"{'=' * 60}")
|
||||||
|
|
||||||
|
write_stats(STATS_FILE, {
|
||||||
|
"source": "Realingo",
|
||||||
|
"timestamp": _run_ts,
|
||||||
|
"duration_sec": round(time.time() - _run_start, 1),
|
||||||
|
"success": True,
|
||||||
|
"accepted": len(results),
|
||||||
|
"fetched": len(all_listings),
|
||||||
|
"pages": page - 1,
|
||||||
|
"cache_hits": cache_hits,
|
||||||
|
"excluded": {
|
||||||
|
"dispozice": excluded_category,
|
||||||
|
"cena": excluded_price,
|
||||||
|
"plocha": excluded_area,
|
||||||
|
"bez GPS": excluded_no_gps,
|
||||||
|
"panel/síd": excluded_panel,
|
||||||
|
"patro": excluded_floor,
|
||||||
|
"bez detailu": excluded_detail,
|
||||||
|
},
|
||||||
|
})
|
||||||
return results
|
return results
|
||||||
|
|
||||||
|
|
||||||
@@ -353,8 +377,22 @@ if __name__ == "__main__":
|
|||||||
handlers=[logging.StreamHandler()]
|
handlers=[logging.StreamHandler()]
|
||||||
)
|
)
|
||||||
|
|
||||||
|
_run_ts = datetime.now().isoformat(timespec="seconds")
|
||||||
start = time.time()
|
start = time.time()
|
||||||
|
try:
|
||||||
estates = scrape(max_pages=args.max_pages, max_properties=args.max_properties)
|
estates = scrape(max_pages=args.max_pages, max_properties=args.max_properties)
|
||||||
|
except Exception as e:
|
||||||
|
logger.error(f"Scraper failed: {e}", exc_info=True)
|
||||||
|
write_stats(STATS_FILE, {
|
||||||
|
"source": "Realingo",
|
||||||
|
"timestamp": _run_ts,
|
||||||
|
"duration_sec": round(time.time() - start, 1),
|
||||||
|
"success": False,
|
||||||
|
"accepted": 0,
|
||||||
|
"fetched": 0,
|
||||||
|
"error": str(e),
|
||||||
|
})
|
||||||
|
raise
|
||||||
|
|
||||||
if estates:
|
if estates:
|
||||||
json_path = Path("byty_realingo.json")
|
json_path = Path("byty_realingo.json")
|
||||||
|
|||||||
15
scraper_stats.py
Normal file
15
scraper_stats.py
Normal file
@@ -0,0 +1,15 @@
|
|||||||
|
"""Shared utility for writing per-scraper run statistics to JSON."""
|
||||||
|
from __future__ import annotations
|
||||||
|
|
||||||
|
import json
|
||||||
|
import os
|
||||||
|
from pathlib import Path
|
||||||
|
|
||||||
|
HERE = Path(__file__).parent
|
||||||
|
DATA_DIR = Path(os.environ.get("DATA_DIR", HERE))
|
||||||
|
|
||||||
|
|
||||||
|
def write_stats(filename: str, stats: dict) -> None:
|
||||||
|
"""Write scraper run stats dict to the data directory."""
|
||||||
|
path = DATA_DIR / filename
|
||||||
|
path.write_text(json.dumps(stats, ensure_ascii=False, indent=2), encoding="utf-8")
|
||||||
477
server.py
Normal file
477
server.py
Normal file
@@ -0,0 +1,477 @@
|
|||||||
|
#!/usr/bin/env python3
|
||||||
|
"""
|
||||||
|
General-purpose HTTP server for maru-hleda-byt.
|
||||||
|
|
||||||
|
Serves static files from DATA_DIR and additionally handles:
|
||||||
|
GET /scrapers-status → SSR scraper status page
|
||||||
|
GET /api/ratings → ratings.json contents
|
||||||
|
POST /api/ratings → save entire ratings object
|
||||||
|
GET /api/ratings/export → same as GET, with download header
|
||||||
|
GET /api/status → status.json contents (JSON)
|
||||||
|
GET /api/status/history → scraper_history.json contents (JSON)
|
||||||
|
"""
|
||||||
|
|
||||||
|
from __future__ import annotations
|
||||||
|
|
||||||
|
import functools
|
||||||
|
import json
|
||||||
|
import logging
|
||||||
|
import os
|
||||||
|
import sys
|
||||||
|
from datetime import datetime
|
||||||
|
from http.server import HTTPServer, SimpleHTTPRequestHandler
|
||||||
|
from pathlib import Path
|
||||||
|
|
||||||
|
PORT = int(os.environ.get("SERVER_PORT", 8080))
|
||||||
|
DATA_DIR = Path(os.environ.get("DATA_DIR", "."))
|
||||||
|
RATINGS_FILE = DATA_DIR / "ratings.json"
|
||||||
|
_LOG_LEVEL = getattr(logging, os.environ.get("LOG_LEVEL", "INFO").upper(), logging.INFO)
|
||||||
|
|
||||||
|
logging.basicConfig(
|
||||||
|
level=_LOG_LEVEL,
|
||||||
|
format="%(asctime)s [server] %(levelname)s %(message)s",
|
||||||
|
datefmt="%Y-%m-%dT%H:%M:%S",
|
||||||
|
)
|
||||||
|
log = logging.getLogger(__name__)
|
||||||
|
|
||||||
|
# ── Helpers ──────────────────────────────────────────────────────────────────
|
||||||
|
|
||||||
|
COLORS = {
|
||||||
|
"sreality": "#1976D2",
|
||||||
|
"realingo": "#7B1FA2",
|
||||||
|
"bezrealitky": "#E65100",
|
||||||
|
"idnes": "#C62828",
|
||||||
|
"psn": "#2E7D32",
|
||||||
|
"cityhome": "#00838F",
|
||||||
|
}
|
||||||
|
|
||||||
|
MONTHS_CZ = [
|
||||||
|
"ledna", "února", "března", "dubna", "května", "června",
|
||||||
|
"července", "srpna", "září", "října", "listopadu", "prosince",
|
||||||
|
]
|
||||||
|
|
||||||
|
|
||||||
|
def _load_json(path: Path, default=None):
|
||||||
|
"""Read and parse JSON file; return default on missing or parse error."""
|
||||||
|
log.debug("_load_json: %s", path.resolve())
|
||||||
|
try:
|
||||||
|
if path.exists():
|
||||||
|
return json.loads(path.read_text(encoding="utf-8"))
|
||||||
|
except Exception as e:
|
||||||
|
log.warning("Failed to load %s: %s", path, e)
|
||||||
|
return default
|
||||||
|
|
||||||
|
|
||||||
|
def _fmt_date(iso_str: str) -> str:
|
||||||
|
"""Format ISO timestamp as Czech date string."""
|
||||||
|
try:
|
||||||
|
d = datetime.fromisoformat(iso_str)
|
||||||
|
return f"{d.day}. {MONTHS_CZ[d.month - 1]} {d.year}, {d.hour:02d}:{d.minute:02d}"
|
||||||
|
except Exception:
|
||||||
|
return iso_str
|
||||||
|
|
||||||
|
|
||||||
|
def load_ratings() -> dict:
|
||||||
|
return _load_json(RATINGS_FILE, default={})
|
||||||
|
|
||||||
|
|
||||||
|
def save_ratings(data: dict) -> None:
|
||||||
|
RATINGS_FILE.write_text(
|
||||||
|
json.dumps(data, ensure_ascii=False, indent=2),
|
||||||
|
encoding="utf-8",
|
||||||
|
)
|
||||||
|
|
||||||
|
|
||||||
|
# ── SSR status page ──────────────────────────────────────────────────────────
|
||||||
|
|
||||||
|
_CSS = """\
|
||||||
|
* { margin: 0; padding: 0; box-sizing: border-box; }
|
||||||
|
body {
|
||||||
|
font-family: system-ui, -apple-system, sans-serif;
|
||||||
|
background: #f5f5f5; color: #333;
|
||||||
|
padding: 24px; max-width: 640px; margin: 0 auto;
|
||||||
|
}
|
||||||
|
h1 { font-size: 22px; margin-bottom: 4px; }
|
||||||
|
.subtitle { color: #888; font-size: 13px; margin-bottom: 24px; }
|
||||||
|
.card {
|
||||||
|
background: white; border-radius: 12px; padding: 20px;
|
||||||
|
box-shadow: 0 1px 4px rgba(0,0,0,0.08); margin-bottom: 16px;
|
||||||
|
}
|
||||||
|
.card h2 { font-size: 15px; margin-bottom: 12px; color: #555; }
|
||||||
|
.timestamp { font-size: 28px; font-weight: 700; color: #1976D2; }
|
||||||
|
.timestamp-sub { font-size: 13px; color: #999; margin-top: 2px; }
|
||||||
|
.summary-row {
|
||||||
|
display: flex; justify-content: space-between; align-items: center;
|
||||||
|
padding: 10px 0; border-bottom: 1px solid #f0f0f0;
|
||||||
|
}
|
||||||
|
.summary-row:last-child { border-bottom: none; }
|
||||||
|
.summary-label { font-size: 13px; color: #666; }
|
||||||
|
.summary-value { font-size: 18px; font-weight: 700; }
|
||||||
|
.badge {
|
||||||
|
display: inline-block; padding: 2px 8px; border-radius: 4px;
|
||||||
|
font-size: 11px; font-weight: 600; color: white;
|
||||||
|
}
|
||||||
|
.badge-ok { background: #4CAF50; }
|
||||||
|
.badge-err { background: #F44336; }
|
||||||
|
.badge-skip { background: #FF9800; }
|
||||||
|
.bar-row { display: flex; align-items: center; gap: 8px; margin: 4px 0; }
|
||||||
|
.bar-track { flex: 1; height: 20px; background: #f0f0f0; border-radius: 4px; overflow: hidden; }
|
||||||
|
.bar-fill { height: 100%; border-radius: 4px; }
|
||||||
|
.bar-count { font-size: 12px; width: 36px; font-variant-numeric: tabular-nums; }
|
||||||
|
.loader-wrap {
|
||||||
|
display: flex; flex-direction: column; align-items: center;
|
||||||
|
justify-content: center; padding: 60px 0;
|
||||||
|
}
|
||||||
|
.spinner {
|
||||||
|
width: 40px; height: 40px; border: 4px solid #e0e0e0;
|
||||||
|
border-top-color: #1976D2; border-radius: 50%;
|
||||||
|
animation: spin 0.8s linear infinite;
|
||||||
|
}
|
||||||
|
@keyframes spin { to { transform: rotate(360deg); } }
|
||||||
|
.loader-text { margin-top: 16px; color: #999; font-size: 14px; }
|
||||||
|
.link-row { text-align: center; margin-top: 8px; }
|
||||||
|
.link-row a { color: #1976D2; text-decoration: none; font-size: 14px; }
|
||||||
|
.history-table { width: 100%; border-collapse: collapse; font-size: 12px; }
|
||||||
|
.history-table th {
|
||||||
|
text-align: left; font-weight: 600; color: #999; font-size: 11px;
|
||||||
|
padding: 4px 6px 8px 6px; border-bottom: 2px solid #f0f0f0;
|
||||||
|
}
|
||||||
|
.history-table td { padding: 7px 6px; border-bottom: 1px solid #f5f5f5; vertical-align: middle; }
|
||||||
|
.history-table tr:last-child td { border-bottom: none; }
|
||||||
|
.history-table tr.latest td { background: #f8fbff; font-weight: 600; }
|
||||||
|
.src-nums { display: flex; gap: 4px; flex-wrap: wrap; }
|
||||||
|
.src-chip {
|
||||||
|
display: inline-block; padding: 1px 5px; border-radius: 3px;
|
||||||
|
font-size: 10px; color: white; font-variant-numeric: tabular-nums;
|
||||||
|
}
|
||||||
|
.clickable-row { cursor: pointer; }
|
||||||
|
.clickable-row:hover td { background: #f0f7ff !important; }
|
||||||
|
/* Modal */
|
||||||
|
#md-overlay {
|
||||||
|
position: fixed; inset: 0; background: rgba(0,0,0,0.45);
|
||||||
|
display: flex; align-items: flex-start; justify-content: center;
|
||||||
|
z-index: 1000; padding: 40px 16px; overflow-y: auto;
|
||||||
|
}
|
||||||
|
#md-box {
|
||||||
|
background: white; border-radius: 12px; padding: 24px;
|
||||||
|
width: 100%; max-width: 620px; position: relative;
|
||||||
|
box-shadow: 0 8px 32px rgba(0,0,0,0.24); margin: auto;
|
||||||
|
}
|
||||||
|
#md-close {
|
||||||
|
position: absolute; top: 10px; right: 14px;
|
||||||
|
background: none; border: none; font-size: 26px; cursor: pointer;
|
||||||
|
color: #aaa; line-height: 1;
|
||||||
|
}
|
||||||
|
#md-close:hover { color: #333; }
|
||||||
|
#md-box h3 { font-size: 15px; margin-bottom: 14px; padding-right: 24px; }
|
||||||
|
.md-summary { display: flex; gap: 20px; flex-wrap: wrap; font-size: 13px; margin-bottom: 16px; color: #555; }
|
||||||
|
.md-summary b { color: #333; }
|
||||||
|
.detail-table { width: 100%; border-collapse: collapse; font-size: 12px; }
|
||||||
|
.detail-table th {
|
||||||
|
text-align: left; color: #999; font-size: 11px; font-weight: 600;
|
||||||
|
padding: 4px 8px 6px 0; border-bottom: 2px solid #f0f0f0; white-space: nowrap;
|
||||||
|
}
|
||||||
|
.detail-table td { padding: 6px 8px 6px 0; border-bottom: 1px solid #f5f5f5; vertical-align: top; }
|
||||||
|
.detail-table tr:last-child td { border-bottom: none; }
|
||||||
|
"""
|
||||||
|
|
||||||
|
_SOURCE_ORDER = ["Sreality", "Realingo", "Bezrealitky", "iDNES", "PSN", "CityHome"]
|
||||||
|
_SOURCE_ABBR = ["Sre", "Rea", "Bez", "iDN", "PSN", "CH"]
|
||||||
|
|
||||||
|
|
||||||
|
def _sources_html(sources: list) -> str:
|
||||||
|
if not sources:
|
||||||
|
return ""
|
||||||
|
max_count = max((s.get("accepted", 0) for s in sources), default=1) or 1
|
||||||
|
parts = ['<div class="card"><h2>Zdroje</h2>']
|
||||||
|
for s in sources:
|
||||||
|
name = s.get("name", "?")
|
||||||
|
accepted = s.get("accepted", 0)
|
||||||
|
error = s.get("error")
|
||||||
|
exc = s.get("excluded", {})
|
||||||
|
excluded_total = sum(exc.values()) if isinstance(exc, dict) else s.get("excluded_total", 0)
|
||||||
|
color = COLORS.get(name.lower(), "#999")
|
||||||
|
pct = round(accepted / max_count * 100) if max_count else 0
|
||||||
|
if error:
|
||||||
|
badge = '<span class="badge badge-err">chyba</span>'
|
||||||
|
elif accepted == 0:
|
||||||
|
badge = '<span class="badge badge-skip">0</span>'
|
||||||
|
else:
|
||||||
|
badge = '<span class="badge badge-ok">OK</span>'
|
||||||
|
parts.append(
|
||||||
|
f'<div style="margin-bottom:12px;">'
|
||||||
|
f'<div style="display:flex;justify-content:space-between;align-items:center;margin-bottom:4px;">'
|
||||||
|
f'<span style="font-weight:600;font-size:14px;">{name} {badge}</span>'
|
||||||
|
f'<span style="font-size:12px;color:#999;">{excluded_total} vyloučených</span>'
|
||||||
|
f'</div>'
|
||||||
|
f'<div class="bar-row">'
|
||||||
|
f'<div class="bar-track"><div class="bar-fill" style="width:{pct}%;background:{color};"></div></div>'
|
||||||
|
f'<span class="bar-count">{accepted}</span>'
|
||||||
|
f'</div></div>'
|
||||||
|
)
|
||||||
|
parts.append("</div>")
|
||||||
|
return "".join(parts)
|
||||||
|
|
||||||
|
|
||||||
|
def _history_html(history: list) -> str:
|
||||||
|
if not history:
|
||||||
|
return ""
|
||||||
|
rows = list(reversed(history))
|
||||||
|
parts = [
|
||||||
|
'<div class="card">'
|
||||||
|
'<h2>Historie běhů <span style="font-size:11px;font-weight:400;color:#bbb;">– klikni pro detaily</span></h2>',
|
||||||
|
'<table class="history-table"><thead><tr>',
|
||||||
|
'<th>Datum</th><th>Trvání</th><th>Přijato / Dedup</th><th>Zdroje</th><th>OK</th>',
|
||||||
|
'</tr></thead><tbody>',
|
||||||
|
]
|
||||||
|
for i, entry in enumerate(rows):
|
||||||
|
row_class = ' class="latest clickable-row"' if i == 0 else ' class="clickable-row"'
|
||||||
|
src_map = {s["name"]: s for s in entry.get("sources", []) if "name" in s}
|
||||||
|
chips = "".join(
|
||||||
|
f'<span class="src-chip" style="background:{"#F44336" if (src_map.get(name) or {}).get("error") else COLORS.get(name.lower(), "#999")}" title="{name}">'
|
||||||
|
f'{abbr} {src_map[name].get("accepted", 0) if name in src_map else "-"}</span>'
|
||||||
|
for name, abbr in zip(_SOURCE_ORDER, _SOURCE_ABBR)
|
||||||
|
)
|
||||||
|
ok_badge = (
|
||||||
|
'<span class="badge badge-err">chyba</span>'
|
||||||
|
if entry.get("success") is False
|
||||||
|
else '<span class="badge badge-ok">OK</span>'
|
||||||
|
)
|
||||||
|
dur = f'{entry["duration_sec"]}s' if entry.get("duration_sec") is not None else "-"
|
||||||
|
parts.append(
|
||||||
|
f'<tr{row_class} data-idx="{i}">'
|
||||||
|
f'<td>{_fmt_date(entry.get("timestamp", ""))}</td>'
|
||||||
|
f'<td>{dur}</td>'
|
||||||
|
f'<td>{entry.get("total_accepted", "-")} / {entry.get("deduplicated", "-")}</td>'
|
||||||
|
f'<td><div class="src-nums">{chips}</div></td>'
|
||||||
|
f'<td>{ok_badge}</td>'
|
||||||
|
f'</tr>'
|
||||||
|
)
|
||||||
|
parts.append("</tbody></table></div>")
|
||||||
|
return "".join(parts)
|
||||||
|
|
||||||
|
|
||||||
|
def _modal_script(rows_json: str) -> str:
|
||||||
|
"""Return the modal overlay HTML + JS for the history detail popup."""
|
||||||
|
return (
|
||||||
|
'<div id="md-overlay" style="display:none">'
|
||||||
|
'<div id="md-box"><button id="md-close">×</button>'
|
||||||
|
'<div id="md-body"></div></div></div>\n'
|
||||||
|
'<script>\n(function(){\n'
|
||||||
|
f'var H={rows_json};\n'
|
||||||
|
'var C={"sreality":"#1976D2","realingo":"#7B1FA2","bezrealitky":"#E65100","idnes":"#C62828","psn":"#2E7D32","cityhome":"#00838F"};\n'
|
||||||
|
'var MN=["ledna","února","března","dubna","května","června","července","srpna","září","října","listopadu","prosince"];\n'
|
||||||
|
'function fd(s){var d=new Date(s);return d.getDate()+". "+MN[d.getMonth()]+" "+d.getFullYear()+", "+String(d.getHours()).padStart(2,"0")+":"+String(d.getMinutes()).padStart(2,"0");}\n'
|
||||||
|
'function openModal(idx){\n'
|
||||||
|
' var e=H[idx],src=e.sources||[];\n'
|
||||||
|
' var h="<h3>Detaily b\u011bhu \u2013 "+fd(e.timestamp)+"</h3>";\n'
|
||||||
|
' h+="<div class=\\"md-summary\\">";\n'
|
||||||
|
' if(e.duration_sec!=null) h+="<span><b>Trvání:</b> "+e.duration_sec+"s</span>";\n'
|
||||||
|
' if(e.total_accepted!=null) h+="<span><b>Přijato:</b> "+e.total_accepted+"</span>";\n'
|
||||||
|
' if(e.deduplicated!=null) h+="<span><b>Po dedup:</b> "+e.deduplicated+"</span>";\n'
|
||||||
|
' h+="</div>";\n'
|
||||||
|
' h+="<table class=\\"detail-table\\"><thead><tr>";\n'
|
||||||
|
' h+="<th>Zdroj</th><th>Přijato</th><th>Staženo</th><th>Stránky</th><th>Cache</th><th>Vyloučeno</th><th>Čas</th><th>OK</th>";\n'
|
||||||
|
' h+="</tr></thead><tbody>";\n'
|
||||||
|
' src.forEach(function(s){\n'
|
||||||
|
' var nm=s.name||"?",col=C[nm.toLowerCase()]||"#999";\n'
|
||||||
|
' var exc=s.excluded||{};\n'
|
||||||
|
' var excStr=Object.entries(exc).filter(function(kv){return kv[1]>0;}).map(function(kv){return kv[0]+": "+kv[1];}).join(", ")||"\u2013";\n'
|
||||||
|
' var ok=s.error?"<span class=\\"badge badge-err\\" title=\\""+s.error+"\\">chyba</span>":"<span class=\\"badge badge-ok\\">OK</span>";\n'
|
||||||
|
' var dot="<span style=\\"display:inline-block;width:8px;height:8px;border-radius:50%;background:"+col+";margin-right:5px;\\"></span>";\n'
|
||||||
|
' h+="<tr>";\n'
|
||||||
|
' h+="<td>"+dot+nm+"</td>";\n'
|
||||||
|
' h+="<td>"+(s.accepted!=null?s.accepted:"\u2013")+"</td>";\n'
|
||||||
|
' h+="<td>"+(s.fetched!=null?s.fetched:"\u2013")+"</td>";\n'
|
||||||
|
' h+="<td>"+(s.pages!=null?s.pages:"\u2013")+"</td>";\n'
|
||||||
|
' h+="<td>"+(s.cache_hits!=null?s.cache_hits:"\u2013")+"</td>";\n'
|
||||||
|
' h+="<td style=\\"font-size:11px;color:#666;\\">"+excStr+"</td>";\n'
|
||||||
|
' h+="<td>"+(s.duration_sec!=null?s.duration_sec+"s":"\u2013")+"</td>";\n'
|
||||||
|
' h+="<td>"+ok+"</td></tr>";\n'
|
||||||
|
' });\n'
|
||||||
|
' h+="</tbody></table>";\n'
|
||||||
|
' document.getElementById("md-body").innerHTML=h;\n'
|
||||||
|
' document.getElementById("md-overlay").style.display="flex";\n'
|
||||||
|
'}\n'
|
||||||
|
'function closeModal(){document.getElementById("md-overlay").style.display="none";}\n'
|
||||||
|
'var tb=document.querySelector(".history-table tbody");\n'
|
||||||
|
'if(tb)tb.addEventListener("click",function(e){var tr=e.target.closest("tr[data-idx]");if(tr)openModal(parseInt(tr.dataset.idx,10));});\n'
|
||||||
|
'document.getElementById("md-close").addEventListener("click",closeModal);\n'
|
||||||
|
'document.getElementById("md-overlay").addEventListener("click",function(e){if(e.target===this)closeModal();});\n'
|
||||||
|
'document.addEventListener("keydown",function(e){if(e.key==="Escape")closeModal();});\n'
|
||||||
|
'})();\n</script>'
|
||||||
|
)
|
||||||
|
|
||||||
|
|
||||||
|
def _render_status_html(status: dict | None, history: list, is_running: bool = False) -> str:
|
||||||
|
"""Generate the complete HTML page for /scrapers-status."""
|
||||||
|
head_open = (
|
||||||
|
'<!DOCTYPE html>\n<html lang="cs">\n<head>\n'
|
||||||
|
'<meta charset="UTF-8">\n'
|
||||||
|
'<meta name="viewport" content="width=device-width, initial-scale=1.0">\n'
|
||||||
|
f'<title>Scraper status</title>\n<style>{_CSS}</style>\n'
|
||||||
|
)
|
||||||
|
page_header = '<h1>Scraper status</h1>\n<div class="subtitle">maru-hleda-byt</div>\n'
|
||||||
|
footer = '<div class="link-row"><a href="/mapa_bytu.html">Otevřít mapu</a></div>'
|
||||||
|
|
||||||
|
if status is None:
|
||||||
|
return (
|
||||||
|
head_open + '</head>\n<body>\n' + page_header
|
||||||
|
+ '<div class="card"><p style="color:#F44336">Status není k dispozici.</p></div>\n'
|
||||||
|
+ footer + '\n</body>\n</html>'
|
||||||
|
)
|
||||||
|
|
||||||
|
if is_running:
|
||||||
|
return (
|
||||||
|
head_open
|
||||||
|
+ '<meta http-equiv="refresh" content="30">\n'
|
||||||
|
+ '</head>\n<body>\n' + page_header
|
||||||
|
+ '<div class="loader-wrap"><div class="spinner"></div>'
|
||||||
|
+ '<div class="loader-text">Scraper právě běží…</div></div>\n'
|
||||||
|
+ footer + '\n</body>\n</html>'
|
||||||
|
)
|
||||||
|
|
||||||
|
# ── Done state ────────────────────────────────────────────────────────────
|
||||||
|
ts = status.get("timestamp", "")
|
||||||
|
duration = status.get("duration_sec")
|
||||||
|
total_accepted = status.get("total_accepted", 0)
|
||||||
|
deduplicated = status.get("deduplicated")
|
||||||
|
|
||||||
|
ts_card = (
|
||||||
|
'<div class="card"><h2>Poslední scrape</h2>'
|
||||||
|
f'<div class="timestamp">{_fmt_date(ts)}</div>'
|
||||||
|
+ (f'<div class="timestamp-sub">Trvání: {round(duration)}s</div>' if duration is not None else "")
|
||||||
|
+ '</div>'
|
||||||
|
)
|
||||||
|
|
||||||
|
sum_card = (
|
||||||
|
'<div class="card"><h2>Souhrn</h2>'
|
||||||
|
f'<div class="summary-row"><span class="summary-label">Vyhovujících bytů</span>'
|
||||||
|
f'<span class="summary-value" style="color:#4CAF50">{total_accepted}</span></div>'
|
||||||
|
+ (
|
||||||
|
f'<div class="summary-row"><span class="summary-label">Po deduplikaci (v mapě)</span>'
|
||||||
|
f'<span class="summary-value" style="color:#1976D2">{deduplicated}</span></div>'
|
||||||
|
if deduplicated is not None else ""
|
||||||
|
)
|
||||||
|
+ '</div>'
|
||||||
|
)
|
||||||
|
|
||||||
|
rows_for_js = list(reversed(history))
|
||||||
|
body = (
|
||||||
|
page_header
|
||||||
|
+ ts_card + "\n"
|
||||||
|
+ sum_card + "\n"
|
||||||
|
+ _sources_html(status.get("sources", [])) + "\n"
|
||||||
|
+ _history_html(history) + "\n"
|
||||||
|
+ footer
|
||||||
|
)
|
||||||
|
modal = _modal_script(json.dumps(rows_for_js, ensure_ascii=False))
|
||||||
|
return head_open + '</head>\n<body>\n' + body + '\n' + modal + '\n</body>\n</html>'
|
||||||
|
|
||||||
|
|
||||||
|
# ── HTTP handler ──────────────────────────────────────────────────────────────
|
||||||
|
|
||||||
|
class Handler(SimpleHTTPRequestHandler):
|
||||||
|
def log_message(self, format, *args):
|
||||||
|
pass # suppress default access log; use our own where needed
|
||||||
|
|
||||||
|
def _send_json(self, status: int, body, extra_headers=None):
|
||||||
|
payload = json.dumps(body, ensure_ascii=False).encode("utf-8")
|
||||||
|
self.send_response(status)
|
||||||
|
self.send_header("Content-Type", "application/json; charset=utf-8")
|
||||||
|
self.send_header("Content-Length", str(len(payload)))
|
||||||
|
self.send_header("Access-Control-Allow-Origin", "*")
|
||||||
|
self.send_header("Access-Control-Allow-Methods", "GET, POST, OPTIONS")
|
||||||
|
self.send_header("Access-Control-Allow-Headers", "Content-Type")
|
||||||
|
if extra_headers:
|
||||||
|
for k, v in extra_headers.items():
|
||||||
|
self.send_header(k, v)
|
||||||
|
self.end_headers()
|
||||||
|
self.wfile.write(payload)
|
||||||
|
|
||||||
|
def do_OPTIONS(self):
|
||||||
|
self.send_response(204)
|
||||||
|
self.send_header("Access-Control-Allow-Origin", "*")
|
||||||
|
self.send_header("Access-Control-Allow-Methods", "GET, POST, OPTIONS")
|
||||||
|
self.send_header("Access-Control-Allow-Headers", "Content-Type")
|
||||||
|
self.end_headers()
|
||||||
|
|
||||||
|
def do_GET(self):
|
||||||
|
if self.path.startswith("/api/"):
|
||||||
|
self._handle_api_get()
|
||||||
|
elif self.path.rstrip("/") == "/scrapers-status":
|
||||||
|
self._serve_status_page()
|
||||||
|
else:
|
||||||
|
log.debug("GET %s → static file: %s", self.path, self.translate_path(self.path))
|
||||||
|
super().do_GET()
|
||||||
|
|
||||||
|
def _handle_api_get(self):
|
||||||
|
if self.path in ("/api/ratings", "/api/ratings/export"):
|
||||||
|
ratings = load_ratings()
|
||||||
|
extra = None
|
||||||
|
if self.path == "/api/ratings/export":
|
||||||
|
extra = {"Content-Disposition": 'attachment; filename="ratings.json"'}
|
||||||
|
log.info("GET %s → %d ratings", self.path, len(ratings))
|
||||||
|
self._send_json(200, ratings, extra)
|
||||||
|
elif self.path == "/api/status":
|
||||||
|
data = _load_json(DATA_DIR / "status.json")
|
||||||
|
if data is None:
|
||||||
|
self._send_json(404, {"error": "status not available"})
|
||||||
|
return
|
||||||
|
log.info("GET /api/status → ok")
|
||||||
|
self._send_json(200, data)
|
||||||
|
elif self.path == "/api/status/history":
|
||||||
|
data = _load_json(DATA_DIR / "scraper_history.json", default=[])
|
||||||
|
if not isinstance(data, list):
|
||||||
|
data = []
|
||||||
|
log.info("GET /api/status/history → %d entries", len(data))
|
||||||
|
self._send_json(200, data)
|
||||||
|
else:
|
||||||
|
self._send_json(404, {"error": "not found"})
|
||||||
|
|
||||||
|
def _serve_status_page(self):
|
||||||
|
status = _load_json(DATA_DIR / "status.json")
|
||||||
|
history = _load_json(DATA_DIR / "scraper_history.json", default=[])
|
||||||
|
if not isinstance(history, list):
|
||||||
|
history = []
|
||||||
|
is_running = (DATA_DIR / "scraper_running.json").exists()
|
||||||
|
html = _render_status_html(status, history, is_running)
|
||||||
|
payload = html.encode("utf-8")
|
||||||
|
self.send_response(200)
|
||||||
|
self.send_header("Content-Type", "text/html; charset=utf-8")
|
||||||
|
self.send_header("Content-Length", str(len(payload)))
|
||||||
|
self.end_headers()
|
||||||
|
self.wfile.write(payload)
|
||||||
|
|
||||||
|
def do_POST(self):
|
||||||
|
if self.path == "/api/ratings":
|
||||||
|
length = int(self.headers.get("Content-Length", 0))
|
||||||
|
if length == 0:
|
||||||
|
self._send_json(400, {"error": "empty body"})
|
||||||
|
return
|
||||||
|
try:
|
||||||
|
raw = self.rfile.read(length)
|
||||||
|
data = json.loads(raw.decode("utf-8"))
|
||||||
|
except Exception as e:
|
||||||
|
log.warning("Bad request body: %s", e)
|
||||||
|
self._send_json(400, {"error": "invalid JSON"})
|
||||||
|
return
|
||||||
|
if not isinstance(data, dict):
|
||||||
|
self._send_json(400, {"error": "expected JSON object"})
|
||||||
|
return
|
||||||
|
save_ratings(data)
|
||||||
|
log.info("POST /api/ratings → saved %d ratings", len(data))
|
||||||
|
self._send_json(200, {"ok": True, "count": len(data)})
|
||||||
|
else:
|
||||||
|
self._send_json(404, {"error": "not found"})
|
||||||
|
|
||||||
|
|
||||||
|
if __name__ == "__main__":
|
||||||
|
log.info("Server starting on port %d, data dir: %s", PORT, DATA_DIR)
|
||||||
|
handler = functools.partial(Handler, directory=str(DATA_DIR))
|
||||||
|
server = HTTPServer(("0.0.0.0", PORT), handler)
|
||||||
|
try:
|
||||||
|
server.serve_forever()
|
||||||
|
except KeyboardInterrupt:
|
||||||
|
log.info("Stopped.")
|
||||||
|
sys.exit(0)
|
||||||
204
status.html
204
status.html
@@ -1,204 +0,0 @@
|
|||||||
<!DOCTYPE html>
|
|
||||||
<html lang="cs">
|
|
||||||
<head>
|
|
||||||
<meta charset="UTF-8">
|
|
||||||
<meta name="viewport" content="width=device-width, initial-scale=1.0">
|
|
||||||
<title>Scraper status</title>
|
|
||||||
<style>
|
|
||||||
* { margin: 0; padding: 0; box-sizing: border-box; }
|
|
||||||
body {
|
|
||||||
font-family: system-ui, -apple-system, sans-serif;
|
|
||||||
background: #f5f5f5; color: #333;
|
|
||||||
padding: 24px; max-width: 640px; margin: 0 auto;
|
|
||||||
}
|
|
||||||
h1 { font-size: 22px; margin-bottom: 4px; }
|
|
||||||
.subtitle { color: #888; font-size: 13px; margin-bottom: 24px; }
|
|
||||||
.card {
|
|
||||||
background: white; border-radius: 12px; padding: 20px;
|
|
||||||
box-shadow: 0 1px 4px rgba(0,0,0,0.08); margin-bottom: 16px;
|
|
||||||
}
|
|
||||||
.card h2 { font-size: 15px; margin-bottom: 12px; color: #555; }
|
|
||||||
.timestamp {
|
|
||||||
font-size: 28px; font-weight: 700; color: #1976D2;
|
|
||||||
}
|
|
||||||
.timestamp-ago { font-size: 13px; color: #999; margin-top: 2px; }
|
|
||||||
|
|
||||||
/* Source table */
|
|
||||||
.source-table { width: 100%; border-collapse: collapse; }
|
|
||||||
.source-table td { padding: 8px 0; border-bottom: 1px solid #f0f0f0; font-size: 14px; }
|
|
||||||
.source-table tr:last-child td { border-bottom: none; }
|
|
||||||
.source-table .name { font-weight: 600; }
|
|
||||||
.source-table .count { text-align: right; font-variant-numeric: tabular-nums; }
|
|
||||||
.source-table .rejected { text-align: right; color: #999; font-size: 12px; }
|
|
||||||
.badge {
|
|
||||||
display: inline-block; padding: 2px 8px; border-radius: 4px;
|
|
||||||
font-size: 11px; font-weight: 600; color: white;
|
|
||||||
}
|
|
||||||
.badge-ok { background: #4CAF50; }
|
|
||||||
.badge-err { background: #F44336; }
|
|
||||||
.badge-skip { background: #FF9800; }
|
|
||||||
|
|
||||||
/* Summary bar */
|
|
||||||
.summary-row {
|
|
||||||
display: flex; justify-content: space-between; align-items: center;
|
|
||||||
padding: 10px 0; border-bottom: 1px solid #f0f0f0;
|
|
||||||
}
|
|
||||||
.summary-row:last-child { border-bottom: none; }
|
|
||||||
.summary-label { font-size: 13px; color: #666; }
|
|
||||||
.summary-value { font-size: 18px; font-weight: 700; }
|
|
||||||
|
|
||||||
/* Source bar chart */
|
|
||||||
.bar-row { display: flex; align-items: center; gap: 8px; margin: 4px 0; }
|
|
||||||
.bar-label { width: 90px; font-size: 12px; text-align: right; color: #666; }
|
|
||||||
.bar-track { flex: 1; height: 20px; background: #f0f0f0; border-radius: 4px; overflow: hidden; position: relative; }
|
|
||||||
.bar-fill { height: 100%; border-radius: 4px; transition: width 0.5s ease; }
|
|
||||||
.bar-count { font-size: 12px; width: 36px; font-variant-numeric: tabular-nums; }
|
|
||||||
|
|
||||||
/* Loader */
|
|
||||||
.loader-wrap {
|
|
||||||
display: flex; flex-direction: column; align-items: center;
|
|
||||||
justify-content: center; padding: 60px 0;
|
|
||||||
}
|
|
||||||
.spinner {
|
|
||||||
width: 40px; height: 40px; border: 4px solid #e0e0e0;
|
|
||||||
border-top-color: #1976D2; border-radius: 50%;
|
|
||||||
animation: spin 0.8s linear infinite;
|
|
||||||
}
|
|
||||||
@keyframes spin { to { transform: rotate(360deg); } }
|
|
||||||
.loader-text { margin-top: 16px; color: #999; font-size: 14px; }
|
|
||||||
|
|
||||||
.error-msg { color: #F44336; padding: 40px 0; text-align: center; }
|
|
||||||
.link-row { text-align: center; margin-top: 8px; }
|
|
||||||
.link-row a { color: #1976D2; text-decoration: none; font-size: 14px; }
|
|
||||||
</style>
|
|
||||||
</head>
|
|
||||||
<body>
|
|
||||||
|
|
||||||
<h1>Scraper status</h1>
|
|
||||||
<div class="subtitle">maru-hleda-byt</div>
|
|
||||||
|
|
||||||
<div id="content">
|
|
||||||
<div class="loader-wrap">
|
|
||||||
<div class="spinner"></div>
|
|
||||||
<div class="loader-text">Nacitam status...</div>
|
|
||||||
</div>
|
|
||||||
</div>
|
|
||||||
|
|
||||||
<div class="link-row"><a href="mapa_bytu.html">Otevrit mapu</a></div>
|
|
||||||
|
|
||||||
<script>
|
|
||||||
var COLORS = {
|
|
||||||
sreality: '#1976D2',
|
|
||||||
realingo: '#7B1FA2',
|
|
||||||
bezrealitky: '#E65100',
|
|
||||||
idnes: '#C62828',
|
|
||||||
psn: '#2E7D32',
|
|
||||||
cityhome: '#00838F',
|
|
||||||
};
|
|
||||||
|
|
||||||
function timeAgo(dateStr) {
|
|
||||||
var d = new Date(dateStr);
|
|
||||||
var now = new Date();
|
|
||||||
var diff = Math.floor((now - d) / 1000);
|
|
||||||
if (diff < 60) return 'prave ted';
|
|
||||||
if (diff < 3600) return Math.floor(diff / 60) + ' min zpet';
|
|
||||||
if (diff < 86400) return Math.floor(diff / 3600) + ' hod zpet';
|
|
||||||
return Math.floor(diff / 86400) + ' dni zpet';
|
|
||||||
}
|
|
||||||
|
|
||||||
function formatDate(dateStr) {
|
|
||||||
var d = new Date(dateStr);
|
|
||||||
var day = d.getDate();
|
|
||||||
var months = ['ledna','unora','brezna','dubna','kvetna','cervna',
|
|
||||||
'cervence','srpna','zari','rijna','listopadu','prosince'];
|
|
||||||
var hh = String(d.getHours()).padStart(2, '0');
|
|
||||||
var mm = String(d.getMinutes()).padStart(2, '0');
|
|
||||||
return day + '. ' + months[d.getMonth()] + ' ' + d.getFullYear() + ', ' + hh + ':' + mm;
|
|
||||||
}
|
|
||||||
|
|
||||||
function render(data) {
|
|
||||||
// Check if scrape is currently running
|
|
||||||
if (data.status === 'running') {
|
|
||||||
document.getElementById('content').innerHTML =
|
|
||||||
'<div class="loader-wrap">' +
|
|
||||||
'<div class="spinner"></div>' +
|
|
||||||
'<div class="loader-text">Scraper prave bezi...</div>' +
|
|
||||||
'</div>';
|
|
||||||
setTimeout(loadStatus, 30000);
|
|
||||||
return;
|
|
||||||
}
|
|
||||||
|
|
||||||
var sources = data.sources || [];
|
|
||||||
var totalOk = 0, totalRej = 0;
|
|
||||||
var maxCount = 0;
|
|
||||||
sources.forEach(function(s) {
|
|
||||||
totalOk += s.accepted || 0;
|
|
||||||
totalRej += s.rejected || 0;
|
|
||||||
if (s.accepted > maxCount) maxCount = s.accepted;
|
|
||||||
});
|
|
||||||
|
|
||||||
var html = '';
|
|
||||||
|
|
||||||
// Timestamp card
|
|
||||||
html += '<div class="card">';
|
|
||||||
html += '<h2>Posledni scrape</h2>';
|
|
||||||
html += '<div class="timestamp">' + formatDate(data.timestamp) + '</div>';
|
|
||||||
html += '<div class="timestamp-ago">' + timeAgo(data.timestamp) + '</div>';
|
|
||||||
if (data.duration_sec) {
|
|
||||||
html += '<div class="timestamp-ago">Trvani: ' + Math.round(data.duration_sec) + 's</div>';
|
|
||||||
}
|
|
||||||
html += '</div>';
|
|
||||||
|
|
||||||
// Summary card
|
|
||||||
html += '<div class="card">';
|
|
||||||
html += '<h2>Souhrn</h2>';
|
|
||||||
html += '<div class="summary-row"><span class="summary-label">Vyhovujicich bytu</span><span class="summary-value" style="color:#4CAF50">' + totalOk + '</span></div>';
|
|
||||||
html += '<div class="summary-row"><span class="summary-label">Vyloucenych</span><span class="summary-value" style="color:#999">' + totalRej + '</span></div>';
|
|
||||||
if (data.deduplicated !== undefined) {
|
|
||||||
html += '<div class="summary-row"><span class="summary-label">Po deduplikaci (v mape)</span><span class="summary-value" style="color:#1976D2">' + data.deduplicated + '</span></div>';
|
|
||||||
}
|
|
||||||
html += '</div>';
|
|
||||||
|
|
||||||
// Sources card
|
|
||||||
html += '<div class="card">';
|
|
||||||
html += '<h2>Zdroje</h2>';
|
|
||||||
sources.forEach(function(s) {
|
|
||||||
var color = COLORS[s.name.toLowerCase()] || '#999';
|
|
||||||
var pct = maxCount > 0 ? Math.round((s.accepted / maxCount) * 100) : 0;
|
|
||||||
var badge = s.error
|
|
||||||
? '<span class="badge badge-err">chyba</span>'
|
|
||||||
: (s.accepted === 0 ? '<span class="badge badge-skip">0</span>' : '<span class="badge badge-ok">OK</span>');
|
|
||||||
|
|
||||||
html += '<div style="margin-bottom:12px;">';
|
|
||||||
html += '<div style="display:flex;justify-content:space-between;align-items:center;margin-bottom:4px;">';
|
|
||||||
html += '<span style="font-weight:600;font-size:14px;">' + s.name + ' ' + badge + '</span>';
|
|
||||||
html += '<span style="font-size:12px;color:#999;">' + (s.rejected || 0) + ' vyloucenych</span>';
|
|
||||||
html += '</div>';
|
|
||||||
html += '<div class="bar-row">';
|
|
||||||
html += '<div class="bar-track"><div class="bar-fill" style="width:' + pct + '%;background:' + color + ';"></div></div>';
|
|
||||||
html += '<span class="bar-count">' + (s.accepted || 0) + '</span>';
|
|
||||||
html += '</div>';
|
|
||||||
html += '</div>';
|
|
||||||
});
|
|
||||||
html += '</div>';
|
|
||||||
|
|
||||||
document.getElementById('content').innerHTML = html;
|
|
||||||
}
|
|
||||||
|
|
||||||
function loadStatus() {
|
|
||||||
fetch('status.json?t=' + Date.now())
|
|
||||||
.then(function(r) {
|
|
||||||
if (!r.ok) throw new Error(r.status);
|
|
||||||
return r.json();
|
|
||||||
})
|
|
||||||
.then(render)
|
|
||||||
.catch(function(err) {
|
|
||||||
document.getElementById('content').innerHTML =
|
|
||||||
'<div class="error-msg">Status zatim neni k dispozici.<br><small>(' + err.message + ')</small></div>';
|
|
||||||
});
|
|
||||||
}
|
|
||||||
|
|
||||||
loadStatus();
|
|
||||||
</script>
|
|
||||||
</body>
|
|
||||||
</html>
|
|
||||||
Reference in New Issue
Block a user