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
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
|
# beautifulsoup.py - parser functions for html content
#
# Copyright (C) 2007, 2008, 2009 Arthur de Jong
#
# This program is free software; you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation; either version 2 of the License, or
# (at your option) any later version.
#
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
# GNU General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with this program; if not, write to the Free Software
# Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
#
# The files produced as output from the software do not automatically fall
# under the copyright of the software, unless explicitly stated otherwise.
"""Parser functions for processing HTML content. This module uses the
BeautifulSoup HTML parser and is more flexible than the legacy HTMLParser
module."""
import urlparse
import crawler
import re
import htmlentitydefs
import bs4
import myurllib
from parsers.html import htmlunescape
# pattern for matching http-equiv and content part of
# <meta http-equiv="refresh" content="0;url=URL">
_refreshhttpequivpattern = re.compile('^refresh$', re.I)
_refershcontentpattern = re.compile('^[0-9]+;url=(.*)$', re.I)
# check BeautifulSoup find() function for bugs
# not needed for bs4
#if BeautifulSoup.BeautifulSoup('<foo>').find('foo', bar=True):
# import debugio
# debugio.warn('using buggy version of BeautifulSoup (%s)' % BeautifulSoup.__version__)
def parse(content, link):
"""Parse the specified content and extract an url list, a list of images a
title and an author. The content is assumed to contain HMTL."""
# create parser and feed it the content
soup = bs4.BeautifulSoup(content,
from_encoding=str(link.encoding),
features="lxml")
# fetch document encoding
link.set_encoding(soup.originalEncoding)
# <title>TITLE</title>
title = soup.find('title')
if title and title.string:
link.title = htmlunescape(title.string).strip()
# FIXME: using myurllib.normalizeurl is wrong below, we should probably use
# something like link.urlunescape() to do the escaping and check
# and log at the same time
# <base href="URL">
base = soup.find('base', href=True)
if base:
base = myurllib.normalizeurl(htmlunescape(base['href']).strip())
else:
base = link.url
# <link rel="TYPE" href="URL">
for l in soup.find_all('link', rel=True, href=True):
# Note that l['rel'] could be a list, strictly speaking, so take first element
if l['rel'][0].lower() in ('stylesheet', 'alternate stylesheet', 'icon', 'shortcut icon'):
embed = myurllib.normalizeurl(htmlunescape(l['href']).strip())
if embed:
link.add_embed(urlparse.urljoin(base, embed))
# <meta name="author" content="AUTHOR">
author = soup.find('meta', attrs={'name': re.compile("^author$", re.I), 'content': True})
if author and author['content']:
link.author = htmlunescape(author['content']).strip()
# <meta http-equiv="refresh" content="0;url=URL">
refresh = soup.find('meta', attrs={'http-equiv': _refreshhttpequivpattern, 'content': True})
if refresh and refresh['content']:
try:
child = _refershcontentpattern.search(refresh['content']).group(1)
link.add_child(urlparse.urljoin(base, child))
except AttributeError:
# ignore cases where refresh header parsing causes problems
pass
# <img src="URL">
for img in soup.find_all('img', src=True):
embed = myurllib.normalizeurl(htmlunescape(img['src']).strip())
if embed:
link.add_embed(urlparse.urljoin(base, embed))
# <a href="URL">
for a in soup.find_all('a', href=True):
child = myurllib.normalizeurl(htmlunescape(a['href']).strip())
if child:
link.add_child(urlparse.urljoin(base, child))
# <a name="NAME">
# TODO: consistent url escaping?
for a in soup.find_all('a', attrs={'name': True}):
# get anchor name
a_name = myurllib.normalizeurl(htmlunescape(a['name']).strip())
# if both id and name are used they should be the same
if a.has_attr('id') and a_name != myurllib.normalizeurl(htmlunescape(a['id']).strip()):
link.add_pageproblem(
'anchors defined in name and id attributes do not match')
# add the id anchor anyway
link.add_anchor(myurllib.normalizeurl(htmlunescape(a['id']).strip()))
# add the anchor
link.add_anchor(a_name)
# <ANY id="ID">
for elem in soup.find_all(id=True):
# skip anchor that have a name
if elem.name == 'a' and elem.has_attr('name'):
continue
# add the anchor
link.add_anchor(myurllib.normalizeurl(htmlunescape(elem['id']).strip()))
# <frameset><frame src="URL"...>...</frameset>
for frame in soup.find_all('frame', src=True):
embed = myurllib.normalizeurl(htmlunescape(frame['src']).strip())
if embed:
link.add_embed(urlparse.urljoin(base, embed))
# <iframe src="URL"...>
for frame in soup.find_all('iframe', src=True):
embed = myurllib.normalizeurl(htmlunescape(frame['src']).strip())
if embed:
link.add_embed(urlparse.urljoin(base, embed))
# <object data="URL"...>
for obj in soup.find_all('object', data=True):
embed = myurllib.normalizeurl(htmlunescape(obj['data']).strip())
if embed:
link.add_embed(urlparse.urljoin(base, embed))
# <object><param name="movie" value="URL"...></object>
for para in soup.find_all('param', attrs={'name': 'movie', 'value': True}):
embed = myurllib.normalizeurl(htmlunescape(para['value']).strip())
if embed:
link.add_embed(urlparse.urljoin(base, embed))
# <map><area href="URL"...>...</map>
for area in soup.find_all('area', href=True):
child = myurllib.normalizeurl(htmlunescape(area['href']).strip())
if child:
link.add_child(urlparse.urljoin(base, child))
# <applet code="URL" [archive="URL"]...>
for applet in soup.find_all('applet', code=True):
# if applet has archive tag check that
if applet.has_attr('archive'):
embed = myurllib.normalizeurl(htmlunescape(applet['archive']).strip())
else:
embed = myurllib.normalizeurl(htmlunescape(applet['code']).strip())
if embed:
link.add_embed(urlparse.urljoin(base, embed))
# <embed src="URL"...>
for embedd in soup.find_all('frame', src=True):
embed = myurllib.normalizeurl(htmlunescape(embedd['src']).strip())
if embed:
link.add_embed(urlparse.urljoin(base, embed))
# <embed><param name="movie" value="url"></embed>
for param in soup.find_all('param', attrs={'name': re.compile("^movie$", re.I), 'value': True}):
embed = myurllib.normalizeurl(htmlunescape(param['value']).strip())
if embed:
link.add_embed(urlparse.urljoin(base, embed))
# <style>content</style>
for style in soup.find_all('style'):
if style.string:
# delegate handling of inline css to css module
import parsers.css
parsers.css.parse(htmlunescape(style.string), link, base)
# <ANY style="CSS">
for elem in soup.find_all(style=True):
# delegate handling of inline css to css module
import parsers.css
parsers.css.parse(elem['style'], link, base)
# <script src="url">
for script in soup.find_all('script', src=True):
embed = myurllib.normalizeurl(htmlunescape(script['src']).strip())
if embed:
link.add_embed(urlparse.urljoin(base, embed))
# <body|table|td background="url">
for t in soup.find_all( ('body', 'table', 'td'), background=True):
embed = myurllib.normalizeurl(htmlunescape(t['background']).strip())
if embed:
link.add_embed(urlparse.urljoin(base, embed))
# flag that the link contains a valid page
link.ispage = True
|
