python beautifulsoup get href code example

Example 1: beuatiful soup find a href

from BeautifulSoup import BeautifulSoup

html = '''<a href="some_url">next</a>
<span class="class"><a href="another_url">later</a></span>'''

soup = BeautifulSoup(html)

for a in soup.find_all('a', href=True):
    print "Found the URL:", a['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)for link in soup.findAll('a', attrs={'href': re.compile("^http://")}):    print link.get('href')

Example 4: 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)