Scrapegraph-ai/scrapegraphai/docloaders/scrape_do.py
2024-09-28 09:02:20 +02:00

39 lines
1.4 KiB
Python

"""
Scrape_do module
"""
import urllib.parse
import requests
import urllib3
urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning)
def scrape_do_fetch(token, target_url, use_proxy=False, geoCode=None, super_proxy=False):
"""
Fetches the IP address of the machine associated with the given URL using Scrape.do.
Args:
token (str): The API token for Scrape.do service.
target_url (str): A valid web page URL to fetch its associated IP address.
use_proxy (bool): Whether to use Scrape.do proxy mode. Default is False.
geoCode (str, optional): Specify the country code for
geolocation-based proxies. Default is None.
super_proxy (bool): If True, use Residential & Mobile Proxy Networks. Default is False.
Returns:
str: The raw response from the target URL.
"""
encoded_url = urllib.parse.quote(target_url)
if use_proxy:
proxy_mode_url = f"http://{token}:@proxy.scrape.do:8080"
proxies = {
"http": proxy_mode_url,
"https": proxy_mode_url,
}
params = {"geoCode": geoCode, "super": str(super_proxy).lower()} if geoCode else {}
response = requests.get(target_url, proxies=proxies, verify=False, params=params)
else:
url = f"http://api.scrape.do?token={token}&url={encoded_url}"
response = requests.get(url)
return response.text