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
|
"""
HTMLParser-based link extractor
"""
from HTMLParser import HTMLParser
from urlparse import urljoin
from w3lib.url import safe_url_string
from scrapy.link import Link
from scrapy.utils.python import unique as unique_list
class HtmlParserLinkExtractor(HTMLParser):
def __init__(self, tag="a", attr="href", process=None, unique=False):
HTMLParser.__init__(self)
self.scan_tag = tag if callable(tag) else lambda t: t == tag
self.scan_attr = attr if callable(attr) else lambda a: a == attr
self.process_attr = process if callable(process) else lambda v: v
self.unique = unique
def _extract_links(self, response_text, response_url, response_encoding):
self.reset()
self.feed(response_text)
self.close()
links = unique_list(self.links, key=lambda link: link.url) if self.unique else self.links
ret = []
base_url = urljoin(response_url, self.base_url) if self.base_url else response_url
for link in links:
if isinstance(link.url, unicode):
link.url = link.url.encode(response_encoding)
link.url = urljoin(base_url, link.url)
link.url = safe_url_string(link.url, response_encoding)
link.text = link.text.decode(response_encoding)
ret.append(link)
return ret
def extract_links(self, response):
# wrapper needed to allow to work directly with text
return self._extract_links(response.body, response.url, response.encoding)
def reset(self):
HTMLParser.reset(self)
self.base_url = None
self.current_link = None
self.links = []
def handle_starttag(self, tag, attrs):
if tag == 'base':
self.base_url = dict(attrs).get('href')
if self.scan_tag(tag):
for attr, value in attrs:
if self.scan_attr(attr):
url = self.process_attr(value)
link = Link(url=url)
self.links.append(link)
self.current_link = link
def handle_endtag(self, tag):
if self.scan_tag(tag):
self.current_link = None
def handle_data(self, data):
if self.current_link:
self.current_link.text = self.current_link.text + data
def matches(self, url):
"""This extractor matches with any url, since
it doesn't contain any patterns"""
return True
|
