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
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
|
# Copyright 2002 by Katharine Lindner. All rights reserved.
# This code is part of the Biopython distribution and governed by its
# license. Please see the LICENSE file that should have been included
# as part of this package.
"""
NetCatch enables the user to scan a list of labelled urls and select
a subset to read into a file.
Functions:
get_urls_by_label
get_urls_by_index
get_urls_by_range
select_output_file
"""
import sys
import os
import urllib
from tempfile import mktemp
import sgmllib
import string
from Bio import File
def is_absolute_url( candidate ):
( url_type, url ) = urllib.splittype( candidate )
if( url_type == None ):
return 0
( url_host, url ) = urllib.splithost( url )
if( url_host == None ):
return 0
return 1
"""
ExtractUrls.py
Scans a file in http format and builds a dictionary of urls
"""
class ExtractUrls( sgmllib.SGMLParser ):
def __init__( self ):
sgmllib.SGMLParser.__init__( self )
self.reset()
def reset( self ):
sgmllib.SGMLParser.reset( self )
self.urls = {}
self._inlink = 0
self._pending_url = ''
self.text = ''
def __str__( self ):
output = ''
for key in self.urls.keys():
val = self.urls[ key ]
output = output + '%s : %s\n' % ( key, val )
return output
def extract_urls(self, handle):
self.feed(handle)
return self.urls
def feed(self, handle):
"""feed(self, handle )
Feed in data for scanning. handle is a file-like object
containing html.
"""
if isinstance(handle, File.UndoHandle):
uhandle = handle
else:
uhandle = File.UndoHandle(handle)
text = uhandle.read()
sgmllib.SGMLParser.feed( self, text )
def handle_data(self, data):
if( self._inlink ):
self.text = self.text + data
def start_a( self, attrs ):
self._inlink = 1
for key, val in attrs:
if key.lower() == 'href':
self._pending_url = val
def end_a( self ):
self._inlink = 0
key = self.text
self.text = ''
if not key == '':
key = key.replace( ' ', '_' )
self.urls[ key ] = self._pending_url
class Url:
def __init__( self, label, url ):
assert is_absolute_url( url )
assert type( label ) == type( '' )
self.label = label
self.url = url
class NetCatch:
"""
Decorator for a dictionary of links. Each link is indexed by its label.
Allows the user to select links of interest and read each selection into
its own file. The filename is contructed by appending the label with an
extension of html.
Files can be selected by index, range or label. The destination directory
defaults to the current directory. The user can specify another
dictionary by passing a list of path segments to the constructor.
net_catch = NetCatch()
net_catch = NetCatch( [ 'amylase', 'species' ] )
net_catch.get_all_urls()
net_catch.get_urls_by_label( [ 'pig', 'dog', 'cow' ] )
net_catch.get_urls_by_index( [ 1, 4, 6, 9 ] )
net_catch.get_urls_by_range( 2, 5 )
"""
def __init__( self, path_segments = [] ):
self._urls = {}
self._labels = []
assert type( path_segments ) == type( [] )
self.path_segments = path_segments
self._build_path()
def _build_path( self ):
base_path = os.path.join( '' )
for segment in self.path_segments:
base_path = os.path.join( base_path, segment )
self.base_path = base_path
def __str__( self ):
i = 0
output = ''
for label in self._labels:
output = output + '%d %s: %s\n' % ( i, label, self._urls[ label ] )
i = i + 1
return output
def import_dict( self, href_dict ):
for ( key, val ) in href_dict.items():
self.add_url( key, val )
def add_url( self, label, url ):
assert is_absolute_url( url )
assert type( label ) == type( '' )
self._labels.append( label )
self._urls[ label ] = url
def get_all_urls( self ):
url_opener = urllib.URLopener()
i = 0
for label in self._labels:
base_path = self.base_path
name = '%s%d.htm' % ( label, i )
full_path = os.path.join( base_path, name )
out_handle = open( full_path , "wb" )
i = i + 1
url = self._urls[ label ]
url_handle = url_opener.open( url )
contents = url_handle.read()
out_handle.write( contents )
url_opener.close( )
out_handle.close()
def get_urls_by_label( self, labels ):
url_opener = urllib.URLopener()
for label in labels:
base_path = self.base_path
name = '%s.htm' % ( label )
full_path = os.path.join( base_path, name )
out_handle = open( full_path , "wb" )
url = self._urls[ label ]
url_handle = url_opener.open( url )
contents = url_handle.read()
out_handle.write( contents )
url_opener.close( )
out_handle.close( )
def get_urls_by_index( self, indices ):
url_opener = urllib.URLopener()
for index in indices:
base_path = self.base_path
name = '%s.htm' % self._labels[ index ]
full_path = os.path.join( base_path, name )
out_handle = open( full_path , "wb" )
label = self._labels[ index ]
url = self._urls[ label ]
url_handle = url_opener.open( url )
contents = url_handle.read()
out_handle.write( contents )
url_opener.close( )
out_handle.close( )
def get_urls_by_range( self, low, hi ):
url_opener = urllib.URLopener( )
for index in range( low, hi ):
base_path = self.base_path
name = '%s.htm' % self._labels[ index ]
full_path = os.path.join( base_path, name )
out_handle = open( full_path , "wb" )
label = self._labels[ index ]
url = self._urls[ label ]
url_handle = url_opener.open( url )
contents = url_handle.read()
out_handle.write( contents )
url_opener.close( )
out_handle.close( )
|
