beautifulsoup python extract urls from request code example

Example 1: BeautifulSoup - scraping the link of the website

import requests
from bs4 import BeautifulSoup

page = requests.get('http://www.example.com')
soup = BeautifulSoup(page.content, 'html.parser')

print(soup.select_one('p a').attrs['href'])  # get the link of the website

Example 2: how to pass the current url to beautiful soup html

from selenium import webdriver
from selenium.webdriver.common.keys import Keys
from bs4 import BeautifulSoup

def parse_content(html_doc):
    soup = BeautifulSoup(html_doc, 'html.parser')
    print (soup.title.text)


driver = webdriver.Chrome()
driver.get("http://www.python.org")
assert "Python" in driver.title
elem = driver.find_element_by_name("q")
elem.clear()
elem.send_keys("pycon")
elem.send_keys(Keys.RETURN)
assert "No results found." not in driver.page_source
html_doc = driver.page_source
driver.close()
parse_content(html_doc)

Tags:

Html Example