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
|
# html.py - parser functions for html content
#
# Copyright (C) 2005 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
"""Parser functions for processing HTML content."""
import config
import debugio
import HTMLParser
import urlparse
import re
# the list of mimetypes this module should be able to handle
mimetypes = ('text/html', 'application/xhtml+xml', 'text/x-server-parsed-html')
class _MyHTMLParser(HTMLParser.HTMLParser):
"""A simple subclass of HTMLParser.HTMLParser continuing after errors
and gathering some information from the parsed content."""
def __init__(self):
"""Inialize the menbers in which we collect data from parsing the
document."""
self.collect = None
self.base = None
self.title = None
self.author = None
self.embedded = []
self.children = []
self.errmsg = None
self.errcount = 0
HTMLParser.HTMLParser.__init__(self)
def error(self, message):
"""Override superclass' error() method to ignore errors."""
# construct error message
(lineno, offset) = self.getpos()
if lineno is not None:
message += ", at line %d" % lineno
if offset is not None:
message += ", column %d" % (offset + 1)
# store error message
debugio.debug("parsers.html._MyHTMLParser.error(): problem parsing html: "+message)
if self.errmsg is None:
self.errmsg = message
# increment error count
self.errcount += 1
if self.errcount > 10:
raise HTMLParser.HTMLParseError(message, self.getpos())
def check_for_whole_start_tag(self, i):
"""Override to catch assertion exception."""
try:
return HTMLParser.HTMLParser.check_for_whole_start_tag(self, i)
except AssertionError, e:
debugio.debug("parsers.html._MyHTMLParser.check_for_whole_start_tag(): caugt assertion error")
def handle_starttag(self, tag, attrs):
"""Handle start tags in html."""
# turn attrs into hash
attrs=dict(attrs)
# <title>content</title>
if tag == "title":
self.collect = ""
# <base href="url">
elif tag == "base" and attrs.has_key("href"):
self.base = attrs["href"]
# <link rel="type" href="url">
elif tag == "link" and attrs.has_key("rel") and attrs.has_key("href"):
if attrs["rel"].lower() in ("stylesheet", "alternate stylesheet", "icon", "shortcut icon"):
self.embedded.append(attrs["href"])
# <meta name="author" content="...">
elif tag == "meta" and attrs.has_key("name") and attrs.has_key("content") and attrs["name"].lower() == "author":
if self.author is None:
self.author = attrs["content"]
# <meta http-equiv="refresh" content="0;url=http://ch.tudelft.nl/~arthur/">
elif tag == "meta" and attrs.has_key("http-equiv") and attrs.has_key("content") and attrs["http-equiv"].lower() == "refresh":
pass # TODO: implement
# <img src="url">
elif tag == "img" and attrs.has_key("src"):
self.embedded.append(attrs["src"])
# <a href="url">
elif tag == "a" and attrs.has_key("href"):
self.children.append(attrs["href"])
# <frameset><frame src="url"...>...</frameset>
elif tag == "frame" and attrs.has_key("src"):
self.embedded.append(attrs["src"])
# <map><area href="url"...>...</map>
elif tag == "area" and attrs.has_key("href"):
self.children.append(attrs["href"])
# <applet code="url"...>
elif tag == "applet" and attrs.has_key("code"):
self.embedded.append(attrs["code"])
# <embed src="url"...>
elif tag == "embed" and attrs.has_key("src"):
self.embedded.append(attrs["src"])
# <embed><param name="movie" value="url"></embed>
elif tag == "param" and attrs.has_key("name") and attrs.has_key("value"):
if attrs["name"].lower() == "movie":
self.embedded.append(attrs["value"])
def handle_endtag(self, tag):
"""Handle end tags in html."""
if tag == 'title' and self.title is None:
self.title = self.collect
self.collect = None
def handle_data(self, data):
"""Collect data if we were collecting data."""
if self.collect is not None:
self.collect += data
def _cleanurl(url):
"""Do some translations of url."""
# replace &#nnn; entity refs with proper characters
charEntityPattern = re.compile('&#[0-9]{1,3};')
for charEntity in charEntityPattern.findall(url):
url = url.replace(charEntity,chr(int(charEntity[2:-1])))
return url
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
parser = _MyHTMLParser()
try:
parser.feed(content)
parser.close()
except (HTMLParser.HTMLParseError, AttributeError):
pass
# check for parser errors
if parser.errmsg is not None:
debugio.debug("parsers.html.parse(): problem parsing html: "+parser.errmsg)
link.add_problem('problem parsing html: %s' % parser.errmsg)
pass
# flag that the link contains a valid page
link.ispage = True
# save the title
if parser.title is not None:
link.title = parser.title
# save the author
if parser.author is not None:
link.author = parser.author
# figure out the base of the document (for building the other urls)
base = link.url
if parser.base is not None:
base = parser.base
# list embedded and children
for embed in parser.embedded:
link.add_embed(urlparse.urljoin(base,_cleanurl(embed)))
for child in parser.children:
link.add_child(urlparse.urljoin(base,_cleanurl(child)))
|