Scrape Google News with Pagination

PHOTO EMBED

Mon May 03 2021 13:43:50 GMT+0000 (UTC)

Saved by @ilyazub #webscraping #googlenews

from bs4 import BeautifulSoup
import requests, lxml, urllib.parse


def print_extracted_data_from_url(url):
    headers = {
        "User-Agent":
        "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.102 Safari/537.36 Edge/18.19582"
    }
    response = requests.get(url, headers=headers).text

    soup = BeautifulSoup(response, 'lxml')

    print(f'Current page: {int(soup.select_one(".YyVfkd").text)}')
    print(f'Current URL: {url}')
    print()

    for container in soup.findAll('div', class_='tF2Cxc'):
        head_text = container.find('h3', class_='LC20lb DKV0Md').text
        head_sum = container.find('div', class_='IsZvec').text
        head_link = container.a['href']
        print(head_text)
        print(head_sum)
        print(head_link)
        print()

    return soup.select_one('a#pnnext')


def scrape():
    next_page_node = print_extracted_data_from_url(
        'https://www.google.com/search?hl=en-US&q=cute+animals')

    while next_page_node is not None:
        next_page_url = urllib.parse.urljoin('https://www.google.com',
                                             next_page_node['href'])

        next_page_node = print_extracted_data_from_url(next_page_url)

scrape()
content_copyCOPY

By https://stackoverflow.com/users/15164646

https://stackoverflow.com/a/67071648/1291371