Arthur de Jong

Open Source / Free Software developer

summaryrefslogtreecommitdiffstats
path: root/htmlparse.py
blob: 38e1f13a518810614ba1c5c1fceccb2f3c3e6838 (plain)
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
# Copyright (C) 1998,1999  marduk <marduk@python.net>
# Copyright (C) 2002 Mike Meyer <mwm@mired.org>
#
# 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., 675 Mass Ave, Cambridge, MA 02139, USA.


"""Utilites for parsing HTML and urls"""

import htmllib
import string
import debugio

def urlformat(url,parent=None):
    """ returns a formatted version of URL, which, adds trailing '/'s, if 
    necessary, deletes fragmentation identifiers '#' and expands partial url's 
    based on parent"""
    
    from urlparse import urlparse, urljoin, urlunparse
    
    method=urlparse(url)[0]
    if (method=='') and (parent != None):
        url=urljoin(parent,url)
        #url=basejoin(parent,url)
    parsedlist = list(urlparse(url))
    parsedlist[5]='' # remove fragment
    # parsedlist[4]='' # remove query string
    url = urlunparse(tuple(parsedlist))
    return url


class MyHTMLParser(htmllib.HTMLParser):
    
    def __init__(self,formatter):
        self.imagelist = []
        self.title = None
        self.author = None
        self.base = None
        htmllib.HTMLParser.__init__(self,formatter)
        
    # override handle_image() 
    def handle_image(self,src,alt,*stuff):
        if src not in self.imagelist: self.imagelist.append(src)

    def do_frame(self,attrs):
        for name, val in attrs:
            if name=="src":
                self.anchorlist.append(val)

    def save_bgn(self):
        self.savedata = ''
        

    def save_end(self):
        data = self.savedata
        self.savedata = None
        return data

    def start_title(self, attrs):
        self.save_bgn()

    def end_title(self):
        #if not self.savedata:
        #    self.title = None
        #    return
        self.title = string.join(string.split(self.save_end()))

    def do_meta(self,attrs):
        fields={}
        for name, value in attrs:
            fields[name]=value
        if fields.has_key('name'):
            if string.lower(fields['name']) == 'author':
                if fields.has_key('content'):
                    author = fields['content']
                    self.author = author
                    debugio.write('\tauthor: ' + author)

    # <AREA> for client-side image maps
    def do_area(self,attrs):
        for name, val in attrs:
            if name=="href":
                if val not in self.anchorlist:
                    self.anchorlist.append(val)

    def do_base(self,attrs):
        for name,val in attrs:
            if name=="href":
                self.base = val

def pageLinks(url,page):
    """ returns a list of all the url's in a page.  page should be a file object
    Partial urls will be expanded using <url> parameter unless the page contains
    the <BASE HREF=> tag."""
    import htmllib
    from formatter import NullFormatter

    parser = MyHTMLParser(NullFormatter())
    parser.feed(page)
    parser.close()
    urllist = []
    imagelist = []
        
    title = parser.title
    author = parser.author
    if parser.base is not None:
        parent = parser.base
    else:
        parent = url
    for anchor in parser.anchorlist:
        anchor=urlformat(anchor,parent)
        if anchor not in urllist: urllist.append(anchor)
        
    for image in parser.imagelist:
        image=urlformat(image,parent)
        if image not in imagelist: imagelist.append(image)

    return (urllist, imagelist, title, author)