get all links from a website python beautifulsoup 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'])
Example 2: get all href links beautifulsoup from a website python
from BeautifulSoup import BeautifulSoupimport urllib2import redef getLinks(url): html_page = urllib2.urlopen(url) soup = BeautifulSoup(html_page) links = [] for link in soup.findAll('a', attrs={'href': re.compile("^http://")}): links.append(link.get('href')) return linksprint( getLinks("https://arstechnica.com") )
Example 3: get all href links beautifulsoup from a website python
from BeautifulSoup import BeautifulSoupimport urllib2import rehtml_page = urllib2.urlopen("https://arstechnica.com")soup = BeautifulSoup(html_page)links = []for link in soup.findAll('a', attrs={'href': re.compile("^http://")}): links.append(link.get('href'))print(links)