5 examples of 'beautifulsoup get href text' in Python

29
def _extract_url_links(html):
30
    """extract url links
31
32
    &gt;&gt;&gt; _extract_url_links('aa<a href="link1">link1</a>bb<a href="link2">link2</a>cc')
33
    ['link1', 'link2']
34
    """
35
    soup = BeautifulSoup(html, "html.parser")
36
    return soup.find_all('a')

34
def parse_all_href(self, output):
35
    global all_href_parsed
36
    all_href_parsed = []
37
    for tag in output.findAll('a', href=True):
38
        all_href_parsed.append(tag['href'])
39
    return all_href_parsed

31
@property
32
def text(self):
33
    text = re.sub('<[^>]*>', '', self.html)
34
    text = htmlParser.unescape(text)
35
    return text.strip()

18
def get_text(self, page, index=0):
19
    contents = self.find(page)
20
    if contents is not None and len(contents) > index:
21
        return contents[0].text
22
    return None

6
def get_href(attrs):
7
	"""Retourne la valeur de l'href
8
9
	>>> get_href([('href', '/partners/'), ('target', '_blank')])
10
	'/partners/'
11
	>>> get_href([('class', 'color2'), ('href', 'http://bookre.org/reader?file=677155')])
12
	'http://bookre.org/reader?file=677155'
13
	>>> get_href([('href', 'javascript:void(0)'), ('onclick', 'return false')])
14
	'javascript:void(0)'
15
	"""
16
17
	for attr, value in attrs:
18
		if attr == 'href':
19
			return value
20
	return None