Skip to content

Instantly share code, notes, and snippets.

What would you like to do?
Using urllib, requests, bs4 to scrape the search result
#originally from
import urllib
import requests
from bs4 import BeautifulSoup
# desktop user-agent
USER_AGENT = "Mozilla/5.0 (Macintosh; Intel Mac OS X 10.14; rv:65.0) Gecko/20100101 Firefox/65.0"
# mobile user-agent
MOBILE_USER_AGENT = "Mozilla/5.0 (Linux; Android 7.0; SM-G930V Build/NRD90M) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/59.0.3071.125 Mobile Safari/537.36"
query = "tensorflow"
query = query.replace(' ', '+')
URL = f"{query}"
headers = {"user-agent": USER_AGENT}
resp = requests.get(URL, headers=headers)
if resp.status_code == 200:
soup = BeautifulSoup(resp.content, "html.parser")
results = []
for g in soup.find_all('div', class_='r'):
anchors = g.find_all('a')
if anchors:
link = anchors[0]['href']
title = g.find('h3').text
item = {
"title": title,
"link": link
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment