1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
|
lxml.html adds a find_class method to elements::
>>> from lxml.etree import Comment
>>> from lxml.html import document_fromstring, fragment_fromstring, tostring
>>> from lxml.html.clean import clean, clean_html
>>> from lxml.html import usedoctest
>>> try: unicode = __builtins__["unicode"]
... except (KeyError, NameError): unicode = str
>>> h = document_fromstring('''
... <html><head></head>
... <body>
... <a class="vcard
... fn url" href="foobar">P1</a>
... <a class="not-fn vcard" href="baz">P2</a>
... </body></html>''')
>>> print(tostring(h, encoding=unicode))
<html>
<head></head>
<body>
<a class="vcard
fn url" href="foobar">P1</a>
<a class="not-fn vcard" href="baz">P2</a>
</body>
</html>
>>> print([e.text for e in h.find_class('fn')])
['P1']
>>> print([e.text for e in h.find_class('vcard')])
['P1', 'P2']
Also added is a get_rel_links, which you can use to search for links
like ``<a rel="$something">``::
>>> h = document_fromstring('''
... <a href="1">test 1</a>
... <a href="2" rel="tag">item 2</a>
... <a href="3" rel="tagging">item 3</a>
... <a href="4" rel="TAG">item 4</a>''')
>>> print([e.attrib['href'] for e in h.find_rel_links('tag')])
['2', '4']
>>> print([e.attrib['href'] for e in h.find_rel_links('nofollow')])
[]
Another method is ``get_element_by_id`` that does what it says::
>>> print(tostring(fragment_fromstring('''
... <div>
... <span id="test">stuff</span>
... </div>''').get_element_by_id('test'), encoding=unicode))
<span id="test">stuff</span>
Or to get the content of an element without the tags, use text_content()::
>>> el = fragment_fromstring('''
... <div>This is <a href="foo">a <b>bold</b> link</a></div>''')
>>> el.text_content()
'This is a bold link'
Or drop an element (leaving its content) or the entire tree, like::
>>> doc = document_fromstring('''
... <html>
... <body>
... <div id="body">
... This is a <a href="foo" id="link">test</a> of stuff.
... </div>
... <!-- a comment -->
... <div>footer</div>
... </body>
... </html>''')
>>> doc.get_element_by_id('link').drop_tag()
>>> print(tostring(doc, encoding=unicode))
<html>
<body>
<div id="body">
This is a test of stuff.
</div>
<!-- a comment -->
<div>footer</div>
</body>
</html>
>>> doc.get_element_by_id('body').drop_tree()
>>> print(tostring(doc, encoding=unicode))
<html>
<body>
<!-- a comment -->
<div>footer</div>
</body>
</html>
Note, however, that comment text will not be merged into the tree when you
drop the comment. Here, ``drop_tag()`` behaves exactly like ``drop_tree()``:
>>> for comment in doc.getiterator(Comment):
... comment.drop_tag()
>>> print(tostring(doc, encoding=unicode))
<html>
<body>
<div>footer</div>
</body>
</html>
|
