Python/web_programming/crawl_google_results.py
Maxim Smolskiy 2702bf9400
Enable ruff S113 rule ()
* Enable ruff S113 rule

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

---------

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
2024-04-21 19:34:18 +02:00

25 lines
811 B
Python

import sys
import webbrowser
import requests
from bs4 import BeautifulSoup
from fake_useragent import UserAgent
if __name__ == "__main__":
print("Googling.....")
url = "https://www.google.com/search?q=" + " ".join(sys.argv[1:])
res = requests.get(url, headers={"UserAgent": UserAgent().random}, timeout=10)
# res.raise_for_status()
with open("project1a.html", "wb") as out_file: # only for knowing the class
for data in res.iter_content(10000):
out_file.write(data)
soup = BeautifulSoup(res.text, "html.parser")
links = list(soup.select(".eZt8xd"))[:5]
print(len(links))
for link in links:
if link.text == "Maps":
webbrowser.open(link.get("href"))
else:
webbrowser.open(f"https://google.com{link.get('href')}")