forked from scrapfly/scrapfly-scrapers
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathrun.py
40 lines (32 loc) · 1.31 KB
/
run.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
"""
This example run script shows how to run the zoopla.com scraper defined in ./zoopla.py
It scrapes ads data and saves it to ./results/
To run this script set the env variable $SCRAPFLY_KEY with your scrapfly API key:
$ export $SCRAPFLY_KEY="your key from https://scrapfly.io/dashboard"
"""
import asyncio
import json
from pathlib import Path
import zoopla
output = Path(__file__).parent / "results"
output.mkdir(exist_ok=True)
async def run():
# enable scrapfly cache for basic use
zoopla.BASE_CONFIG["cache"] = True
print("running zoopla scrape and saving results to ./results directory")
properties_data = await zoopla.scrape_properties(
urls=["https://www.zoopla.co.uk/for-sale/details/65901787/"]
)
with open(output.joinpath("properties.json"), "w", encoding="utf-8") as file:
json.dump(properties_data, file, indent=2, ensure_ascii=False)
search_data = await zoopla.scrape_search(
scrape_all_pages=False,
max_scrape_pages=2,
# make sure you query is valid first by using it in the search
query="Islington, London",
query_type= "for-sale"
)
with open(output.joinpath("search.json"), "w", encoding="utf-8") as file:
json.dump(search_data, file, indent=2, ensure_ascii=False)
if __name__ == "__main__":
asyncio.run(run())