Python/web_programming/crawl_google_results.py
Christian Clauss 5f4da5d616
isort --profile black . (#2181)
* updating DIRECTORY.md

* isort --profile black .

* Black after

* updating DIRECTORY.md

Co-authored-by: github-actions <${GITHUB_ACTOR}@users.noreply.github.com>
2020-07-06 09:44:19 +02:00

25 lines
798 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})
# 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"http://google.com{link.get('href')}")