Created
February 8, 2021 11:10
-
-
Save prykon/976f7e1f66bf7ada8c094ca5defadb45 to your computer and use it in GitHub Desktop.
Scrape Top Stories URLs and titles from Google SERPs.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#Scrape Google SERPs for Top Stories URLs and titles | |
import requests | |
from bs4 import BeautifulSoup | |
keyword = 'keyword goes here' | |
url = 'https://www.google.com/search?q=%s' % keyword | |
source = requests.get(url).content | |
soup = BeautifulSoup(source, 'lxml') | |
result_url = soup.find_all("div", {"class":"HCUNre"}) | |
result_text = soup.find_all("div", {"class":"nDgy9d"}) | |
i=0 | |
output_urls = [] | |
output_text = [] | |
output_rows = [] | |
for r in result_url: | |
output_urls.append(r.find('a')['href'].strip()) | |
for r in result_text: | |
output_text.append(r.text.strip()) | |
for i in range(len(output_urls)): | |
output_rows.append('%s;%s' % (output_urls[i], output_text[i])) | |
print('%s;%s' % (output_urls[i], output_text[i])) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment