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
|
# Authors: John Dennis <jdennis@redhat.com>
#
# Copyright (C) 2007 Red Hat, Inc.
#
# 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.
#
__all__ = [
'escape_html',
'unescape_html',
'html_to_text',
'html_document',
]
import htmllib
import formatter as Formatter
import string
from types import *
try:
from io import StringIO
except ImportError:
from StringIO import StringIO
#------------------------------------------------------------------------------
class TextWriter(Formatter.DumbWriter):
def __init__(self, file=None, maxcol=80, indent_width=4):
Formatter.DumbWriter.__init__(self, file, maxcol)
self.indent_level = 0
self.indent_width = indent_width
self._set_indent()
def _set_indent(self):
self.indent_col = self.indent_level * self.indent_width
self.indent = ' ' * self.indent_col
def new_margin(self, margin, level):
self.indent_level = level
self._set_indent()
def send_label_data(self, data):
data = data + ' '
if len(data) > self.indent_col:
self.send_literal_data(data)
else:
offset = self.indent_col - len(data)
self.send_literal_data(' ' * offset + data)
def send_flowing_data(self, data):
if not data:
return
atbreak = self.atbreak or data[0] in string.whitespace
col = self.col
maxcol = self.maxcol
write = self.file.write
col = self.col
if col == 0:
write(self.indent)
col = self.indent_col
for word in data.split():
if atbreak:
if col + len(word) >= maxcol:
write('\n' + self.indent)
col = self.indent_col
else:
write(' ')
col = col + 1
write(word)
col = col + len(word)
atbreak = 1
self.col = col
self.atbreak = data[-1] in string.whitespace
class HTMLParserAnchor(htmllib.HTMLParser):
def __init__(self, formatter, verbose=0):
htmllib.HTMLParser.__init__(self, formatter, verbose)
def anchor_bgn(self, href, name, type):
self.anchor = href
def anchor_end(self):
if self.anchor:
self.handle_data(' (%s) ' % self.anchor)
self.anchor = None
#------------------------------------------------------------------------------
def escape_html(s):
if s is None:
return None
s = s.replace("&", "&") # Must be done first!
s = s.replace("<", "<")
s = s.replace(">", ">")
s = s.replace("'", "'")
s = s.replace('"', """)
return s
def unescape_html(s):
if s is None:
return None
if '&' not in s:
return s
s = s.replace("<", "<")
s = s.replace(">", ">")
s = s.replace("'", "'")
s = s.replace(""", '"')
s = s.replace("&", "&") # Must be last
return s
def html_to_text(html, maxcol=80):
try:
buffer = StringIO()
formatter = Formatter.AbstractFormatter(TextWriter(buffer, maxcol))
parser = HTMLParserAnchor(formatter)
parser.feed(html)
parser.close()
text = buffer.getvalue()
buffer.close()
return text
except Exception as e:
log_program.error('cannot convert html to text: %s' % e)
return None
def html_document(*body_components):
'''Wrap the body components in a HTML document structure with a valid header.
Accepts a variable number of arguments of of which canb be:
* string
* a sequences of strings (tuple or list).
* a callable object taking no parameters and returning a string or sequence of strings.
'''
head = '<html>\n <head>\n <meta http-equiv="Content-Type" content="text/html; charset=utf-8"/>\n </head>\n <body>\n'
tail = '\n </body>\n</html>'
doc = head
for body_component in body_components:
if type(body_component) is StringTypes:
doc += body_component
elif type(body_component) in [TupleType, ListType]:
for item in body_component:
doc += item
elif callable(body_component):
result = body_component()
if type(result) in [TupleType, ListType]:
for item in result:
doc += item
else:
doc += result
else:
doc += body_component
doc += tail
return doc
|
