« back to all changes in this revision
Viewing changes to html2text.py
- browse files at revision 4
- compare with another revision
- download diff
- download tarball
- view history from revision 4
- Committer: Bazaar Package Importer
- Author(s): Joey Hess
- Date: 2006-12-13 14:34:42 UTC
- mfrom: (2.1.7 feisty)
- Revision ID: james.westby@ubuntu.com-20061213143442-bdyafysycipud6q6
Tags: 1:2.60-3
Check exit status of sendmail, and die if it fails. Closes: #402725
- files added:
- debian/README.Debian
- files removed:
- feedparser.py
- files modified:
- config.py
- r2e *
added
removed
html2text.py
1
"""html2text: Turn HTML into equivalent Markdown-structured text."""
2
__version__ = "2.2"
3
__author__ = "Aaron Swartz (me@aaronsw.com)"
4
__copyright__ = "(C) 2004 Aaron Swartz. GNU GPL 2."
5
__contributors__ = ["Martin 'Joey' Schulze"]
6
7
# TODO:
8
# Support decoded entities with unifiable.
9
# Word wrap.
10
# Fix :s using buffering
11
# Relative URl resolution
12
13
import re, sys, urllib, htmlentitydefs, codecs, StringIO, types
14
import sgmllib
15
sgmllib.charref = re.compile('&#([xX]?[0-9a-fA-F]+)[^0-9a-fA-F]')
16
17
try: from textwrap import wrap
18
except: pass
19
20
# Use Unicode characters instead of their ascii psuedo-replacements
21
UNICODE_SNOB = 0
22
23
# Put the links after each paragraph instead of at the end.
24
LINKS_EACH_PARAGRAPH = 0
25
26
# Wrap long lines at position. 0 for no wrapping. (Requires Python 2.3.)
27
BODY_WIDTH = 0
28
29
### Entity Nonsense ###
30
31
def name2cp(k):
32
if k == 'apos': return ord("'")
33
if hasattr(htmlentitydefs, "name2codepoint"): # requires Python 2.3
34
return htmlentitydefs.name2codepoint[k]
35
else:
36
k = htmlentitydefs.entitydefs[k]
37
if k.startswith("&#") and k.endswith(";"): return int(k[2:-1]) # not in latin-1
38
return ord(codecs.latin_1_decode(k)[0])
39
40
unifiable = {'rsquo':"'", 'lsquo':"'", 'rdquo':'"', 'ldquo':'"',
41
'copy':'(C)', 'mdash':'--', 'nbsp':' ', 'rarr':'->', 'larr':'<-', 'middot':'*',
42
'ndash':'-', 'oelig':'oe', 'aelig':'ae',
43
'agrave':'a', 'aacute':'a', 'acirc':'a', 'atilde':'a', 'auml':'a', 'aring':'a',
44
'egrave':'e', 'eacute':'e', 'ecirc':'e', 'euml':'e',
45
'igrave':'i', 'iacute':'i', 'icirc':'i', 'iuml':'i',
46
'ograve':'o', 'oacute':'o', 'ocirc':'o', 'otilde':'o', 'ouml':'o',
47
'ugrave':'u', 'uacute':'u', 'ucirc':'u', 'uuml':'u'}
48
49
unifiable_n = {}
50
51
for k in unifiable.keys():
52
unifiable_n[name2cp(k)] = unifiable[k]
53
54
def charref(name):
55
if name[0] in ['x','X']:
56
c = int(name[1:], 16)
57
else:
58
c = int(name)
59
60
if not UNICODE_SNOB and c in unifiable_n.keys():
61
return unifiable_n[c]
62
else:
63
return unichr(c)
64
65
def entityref(c):
66
if not UNICODE_SNOB and c in unifiable.keys():
67
return unifiable[c]
68
else:
69
try: name2cp(c)
70
except KeyError: return "&" + c
71
else: return unichr(name2cp(c))
72
73
def replaceEntities(s):
74
s = s.group(1)
75
if s[0] == "#":
76
return charref(s[1:])
77
else: return entityref(s)
78
79
r_unescape = re.compile(r"&(#?[xX]?(?:[0-9a-fA-F]+|\w{1,8}));")
80
def unescape(s):
81
return r_unescape.sub(replaceEntities, s)
82
83
def fixattrs(attrs):
84
# Fix bug in sgmllib.py
85
if not attrs: return attrs
86
newattrs = []
87
for attr in attrs:
88
newattrs.append((attr[0], unescape(attr[1])))
89
return newattrs
90
91
### End Entity Nonsense ###
92
93
def onlywhite(line):
94
"""Return true if the line does only consist of whitespace characters."""
95
for c in line:
96
if c is not ' ' and c is not ' ':
97
return c is ' '
98
return line
99
100
def optwrap(text):
101
"""Wrap all paragraphs in the provided text."""
102
if not BODY_WIDTH:
103
return text
104
105
assert wrap # Requires Python 2.3.
106
result = ''
107
newlines = 0
108
for para in text.split("\n"):
109
if len(para) > 0:
110
if para[0] is not ' ' and para[0] is not '-' and para[0] is not '*':
111
for line in wrap(para, BODY_WIDTH):
112
result += line + "\n"
113
result += "\n"
114
newlines = 2
115
else:
116
if not onlywhite(para):
117
result += para + "\n"
118
newlines = 1
119
else:
120
if newlines < 2:
121
result += "\n"
122
newlines += 1
123
return result
124
125
def hn(tag):
126
if tag[0] == 'h' and len(tag) == 2:
127
try:
128
n = int(tag[1])
129
if n in range(1, 10): return n
130
except ValueError: return 0
131
132
class _html2text(sgmllib.SGMLParser):
133
def __init__(self, out=sys.stdout.write):
134
sgmllib.SGMLParser.__init__(self)
135
136
if out is None: self.out = self.outtextf
137
else: self.out = out
138
self.outtext = u''
139
self.quiet = 0
140
self.p_p = 0
141
self.outcount = 0
142
self.start = 1
143
self.space = 0
144
self.a = []
145
self.astack = []
146
self.acount = 0
147
self.list = []
148
self.blockquote = 0
149
self.pre = 0
150
self.startpre = 0
151
self.lastWasNL = 0
152
153
def outtextf(self, s):
154
if type(s) is type(''): s = codecs.utf_8_decode(s)[0]
155
self.outtext += s
156
157
def close(self):
158
sgmllib.SGMLParser.close(self)
159
160
self.pbr()
161
self.o('', 0, 'end')
162
163
return self.outtext
164
165
def handle_charref(self, c):
166
self.o(charref(c))
167
168
def handle_entityref(self, c):
169
self.o(entityref(c))
170
171
def unknown_starttag(self, tag, attrs):
172
self.handle_tag(tag, attrs, 1)
173
174
def unknown_endtag(self, tag):
175
self.handle_tag(tag, None, 0)
176
177
def previousIndex(self, attrs):
178
""" returns the index of certain set of attributes (of a link) in the
179
self.a list
180
181
If the set of attributes is not found, returns None
182
"""
183
if not attrs.has_key('href'): return None
184
185
i = -1
186
for a in self.a:
187
i += 1
188
match = 0
189
190
if a.has_key('href') and a['href'] == attrs['href']:
191
if a.has_key('title') or attrs.has_key('title'):
192
if (a.has_key('title') and attrs.has_key('title') and
193
a['title'] == attrs['title']):
194
match = True
195
else:
196
match = True
197
198
if match: return i
199
200
def handle_tag(self, tag, attrs, start):
201
attrs = fixattrs(attrs)
202
203
if hn(tag):
204
self.p()
205
if start: self.o(hn(tag)*"#" + ' ')
206
207
if tag in ['p', 'div']: self.p()
208
209
if tag == "br" and start: self.o(" \n")
210
211
if tag == "hr" and start:
212
self.p()
213
self.o("* * *")
214
self.p()
215
216
if tag in ["head", "style", 'script']:
217
if start: self.quiet += 1
218
else: self.quiet -= 1
219
220
if tag == "blockquote":
221
if start:
222
self.p(); self.o('> ', 0, 1); self.start = 1
223
self.blockquote += 1
224
else:
225
self.blockquote -= 1
226
self.p()
227
228
if tag in ['em', 'i', 'u']: self.o("_")
229
if tag in ['strong', 'b']: self.o("**")
230
if tag == "code" and not self.pre: self.o('`') #TODO: `` `this` ``
231
232
if tag == "a":
233
if start:
234
attrsD = {}
235
for (x, y) in attrs: attrsD[x] = y
236
attrs = attrsD
237
if attrs.has_key('href'):
238
self.astack.append(attrs)
239
self.o("[")
240
else:
241
self.astack.append(None)
242
else:
243
if self.astack:
244
a = self.astack.pop()
245
if a:
246
i = self.previousIndex(a)
247
if i is not None:
248
a = self.a[i]
249
else:
250
self.acount += 1
251
a['count'] = self.acount
252
a['outcount'] = self.outcount
253
self.a.append(a)
254
self.o("][" + `a['count']` + "]")
255
256
if tag == "img" and start:
257
attrsD = {}
258
for (x, y) in attrs: attrsD[x] = y
259
attrs = attrsD
260
if attrs.has_key('src'):
261
attrs['href'] = attrs['src']
262
alt = attrs.get('alt', '')
263
alt = re.sub('\n', ' ', alt)
264
i = self.previousIndex(attrs)
265
if i is not None:
266
attrs = self.a[i]
267
else:
268
self.acount += 1
269
attrs['count'] = self.acount
270
attrs['outcount'] = self.outcount
271
self.a.append(attrs)
272
self.o("![")
273
self.o(alt)
274
self.o("]["+`attrs['count']`+"]")
275
276
if tag in ["ol", "ul"]:
277
if start:
278
self.list.append({'name':tag, 'num':0})
279
else:
280
self.list.pop()
281
282
self.p()
283
284
if tag == 'li':
285
if start:
286
self.pbr()
287
if self.list: li = self.list[-1]
288
else: li = {'name':'ul', 'num':0}
289
self.o(" "*len(self.list)) #TODO: line up <ol><li>s > 9 correctly.
290
if li['name'] == "ul": self.o("* ")
291
elif li['name'] == "ol":
292
li['num'] += 1
293
self.o(`li['num']`+". ")
294
self.start = 1
295
else:
296
self.pbr()
297
298
if tag in ['tr']: self.pbr()
299
300
if tag == "pre":
301
if start:
302
self.startpre = 1
303
self.pre = 1
304
else:
305
self.pre = 0
306
self.p()
307
308
def pbr(self):
309
if self.p_p == 0: self.p_p = 1
310
311
def p(self): self.p_p = 2
312
313
314
def o(self, data, puredata=0, force=0):
315
if not self.quiet:
316
if puredata and not self.pre:
317
data = re.sub('\s+', ' ', data)
318
if data and data[0] == ' ':
319
self.space = 1
320
data = data[1:]
321
if not data and not force: return
322
323
if self.startpre:
324
self.out(" :") #TODO: not output when already one there
325
self.startpre = 0
326
327
bq = (">" * self.blockquote)
328
if not (force and data and data[0] == ">") and self.blockquote: bq += " "
329
330
if self.pre:
331
bq += " "
332
data = data.replace("\n", "\n"+bq)
333
334
if self.start:
335
self.space = 0
336
self.p_p = 0
337
self.start = 0
338
339
if force == 'end':
340
# It's the end.
341
self.p_p = 0
342
self.out("\n")
343
self.space = 0
344
345
346
if self.p_p:
347
self.out(('\n'+bq)*self.p_p)
348
self.space = 0
349
350
if self.space:
351
if not self.lastWasNL: self.out(' ')
352
self.space = 0
353
354
if self.a and ((self.p_p == 2 and LINKS_EACH_PARAGRAPH) or force == "end"):
355
if force == "end": self.out("\n")
356
357
newa = []
358
for link in self.a:
359
if self.outcount > link['outcount']:
360
self.out(" ["+`link['count']`+"]: " + link['href']) #TODO: base href
361
if link.has_key('title'): self.out(" ("+link['title']+")")
362
self.out("\n")
363
else:
364
newa.append(link)
365
366
if self.a != newa: self.out("\n") # Don't need an extra line when nothing was done.
367
368
self.a = newa
369
370
self.p_p = 0
371
self.out(data)
372
self.lastWasNL = data and data[-1] == '\n'
373
self.outcount += 1
374
375
def handle_data(self, data):
376
self.o(data, 1)
377
378
def unknown_decl(self, data): pass
379
380
def html2text_file(html, out=sys.stdout.write):
381
h = _html2text(out)
382
h.feed(html)
383
h.feed("")
384
return h.close()
385
386
def html2text(html):
387
return optwrap(html2text_file(html, None))
388
389
if __name__ == "__main__":
390
if sys.argv[1:]:
391
arg = sys.argv[1]
392
if arg.startswith('http://'):
393
data = urllib.urlopen(arg).read()
394
else:
395
data = open(arg, 'r').read()
396
else:
397
data = sys.stdin.read()
398
html2text_file(data)
1
"""html2text: Turn HTML into equivalent Markdown-structured text."""
2
__version__ = "2.24"
3
__author__ = "Aaron Swartz (me@aaronsw.com)"
4
__copyright__ = "(C) 2004 Aaron Swartz. GNU GPL 2."
5
__contributors__ = ["Martin 'Joey' Schulze", "Ricardo Reyes"]
6
7
# TODO:
8
# Support decoded entities with unifiable.
9
# Relative URL resolution
10
11
if not hasattr(__builtins__, 'True'): True, False = 1, 0
12
import re, sys, urllib, htmlentitydefs, codecs, StringIO, types
13
import sgmllib
14
sgmllib.charref = re.compile('&#([xX]?[0-9a-fA-F]+)[^0-9a-fA-F]')
15
16
try: from textwrap import wrap
17
except: pass
18
19
# Use Unicode characters instead of their ascii psuedo-replacements
20
UNICODE_SNOB = 0
21
22
# Put the links after each paragraph instead of at the end.
23
LINKS_EACH_PARAGRAPH = 0
24
25
# Wrap long lines at position. 0 for no wrapping. (Requires Python 2.3.)
26
BODY_WIDTH = 0
27
28
### Entity Nonsense ###
29
30
def name2cp(k):
31
if k == 'apos': return ord("'")
32
if hasattr(htmlentitydefs, "name2codepoint"): # requires Python 2.3
33
return htmlentitydefs.name2codepoint[k]
34
else:
35
k = htmlentitydefs.entitydefs[k]
36
if k.startswith("&#") and k.endswith(";"): return int(k[2:-1]) # not in latin-1
37
return ord(codecs.latin_1_decode(k)[0])
38
39
unifiable = {'rsquo':"'", 'lsquo':"'", 'rdquo':'"', 'ldquo':'"',
40
'copy':'(C)', 'mdash':'--', 'nbsp':' ', 'rarr':'->', 'larr':'<-', 'middot':'*',
41
'ndash':'-', 'oelig':'oe', 'aelig':'ae',
42
'agrave':'a', 'aacute':'a', 'acirc':'a', 'atilde':'a', 'auml':'a', 'aring':'a',
43
'egrave':'e', 'eacute':'e', 'ecirc':'e', 'euml':'e',
44
'igrave':'i', 'iacute':'i', 'icirc':'i', 'iuml':'i',
45
'ograve':'o', 'oacute':'o', 'ocirc':'o', 'otilde':'o', 'ouml':'o',
46
'ugrave':'u', 'uacute':'u', 'ucirc':'u', 'uuml':'u'}
47
48
unifiable_n = {}
49
50
for k in unifiable.keys():
51
unifiable_n[name2cp(k)] = unifiable[k]
52
53
def charref(name):
54
if name[0] in ['x','X']:
55
c = int(name[1:], 16)
56
else:
57
c = int(name)
58
59
if not UNICODE_SNOB and c in unifiable_n.keys():
60
return unifiable_n[c]
61
else:
62
return unichr(c)
63
64
def entityref(c):
65
if not UNICODE_SNOB and c in unifiable.keys():
66
return unifiable[c]
67
else:
68
try: name2cp(c)
69
except KeyError: return "&" + c
70
else: return unichr(name2cp(c))
71
72
def replaceEntities(s):
73
s = s.group(1)
74
if s[0] == "#":
75
return charref(s[1:])
76
else: return entityref(s)
77
78
r_unescape = re.compile(r"&(#?[xX]?(?:[0-9a-fA-F]+|\w{1,8}));")
79
def unescape(s):
80
return r_unescape.sub(replaceEntities, s)
81
82
def fixattrs(attrs):
83
# Fix bug in sgmllib.py
84
if not attrs: return attrs
85
newattrs = []
86
for attr in attrs:
87
newattrs.append((attr[0], unescape(attr[1])))
88
return newattrs
89
90
### End Entity Nonsense ###
91
92
def onlywhite(line):
93
"""Return true if the line does only consist of whitespace characters."""
94
for c in line:
95
if c is not ' ' and c is not ' ':
96
return c is ' '
97
return line
98
99
def optwrap(text):
100
"""Wrap all paragraphs in the provided text."""
101
if not BODY_WIDTH:
102
return text
103
104
assert wrap # Requires Python 2.3.
105
result = ''
106
newlines = 0
107
for para in text.split("\n"):
108
if len(para) > 0:
109
if para[0] is not ' ' and para[0] is not '-' and para[0] is not '*':
110
for line in wrap(para, BODY_WIDTH):
111
result += line + "\n"
112
result += "\n"
113
newlines = 2
114
else:
115
if not onlywhite(para):
116
result += para + "\n"
117
newlines = 1
118
else:
119
if newlines < 2:
120
result += "\n"
121
newlines += 1
122
return result
123
124
def hn(tag):
125
if tag[0] == 'h' and len(tag) == 2:
126
try:
127
n = int(tag[1])
128
if n in range(1, 10): return n
129
except ValueError: return 0
130
131
class _html2text(sgmllib.SGMLParser):
132
def __init__(self, out=sys.stdout.write):
133
sgmllib.SGMLParser.__init__(self)
134
135
if out is None: self.out = self.outtextf
136
else: self.out = out
137
self.outtext = u''
138
self.quiet = 0
139
self.p_p = 0
140
self.outcount = 0
141
self.start = 1
142
self.space = 0
143
self.a = []
144
self.astack = []
145
self.acount = 0
146
self.list = []
147
self.blockquote = 0
148
self.pre = 0
149
self.startpre = 0
150
self.lastWasNL = 0
151
152
def outtextf(self, s):
153
if type(s) is type(''): s = codecs.utf_8_decode(s, "replace")[0]
154
self.outtext += s
155
156
def close(self):
157
sgmllib.SGMLParser.close(self)
158
159
self.pbr()
160
self.o('', 0, 'end')
161
162
return self.outtext
163
164
def handle_charref(self, c):
165
self.o(charref(c))
166
167
def handle_entityref(self, c):
168
self.o(entityref(c))
169
170
def unknown_starttag(self, tag, attrs):
171
self.handle_tag(tag, attrs, 1)
172
173
def unknown_endtag(self, tag):
174
self.handle_tag(tag, None, 0)
175
176
def previousIndex(self, attrs):
177
""" returns the index of certain set of attributes (of a link) in the
178
self.a list
179
180
If the set of attributes is not found, returns None
181
"""
182
if not attrs.has_key('href'): return None
183
184
i = -1
185
for a in self.a:
186
i += 1
187
match = 0
188
189
if a.has_key('href') and a['href'] == attrs['href']:
190
if a.has_key('title') or attrs.has_key('title'):
191
if (a.has_key('title') and attrs.has_key('title') and
192
a['title'] == attrs['title']):
193
match = True
194
else:
195
match = True
196
197
if match: return i
198
199
def handle_tag(self, tag, attrs, start):
200
attrs = fixattrs(attrs)
201
202
if hn(tag):
203
self.p()
204
if start: self.o(hn(tag)*"#" + ' ')
205
206
if tag in ['p', 'div']: self.p()
207
208
if tag == "br" and start: self.o(" \n")
209
210
if tag == "hr" and start:
211
self.p()
212
self.o("* * *")
213
self.p()
214
215
if tag in ["head", "style", 'script']:
216
if start: self.quiet += 1
217
else: self.quiet -= 1
218
219
if tag == "blockquote":
220
if start:
221
self.p(); self.o('> ', 0, 1); self.start = 1
222
self.blockquote += 1
223
else:
224
self.blockquote -= 1
225
self.p()
226
227
if tag in ['em', 'i', 'u']: self.o("_")
228
if tag in ['strong', 'b']: self.o("**")
229
if tag == "code" and not self.pre: self.o('`') #TODO: `` `this` ``
230
231
if tag == "a":
232
if start:
233
attrsD = {}
234
for (x, y) in attrs: attrsD[x] = y
235
attrs = attrsD
236
if attrs.has_key('href'):
237
self.astack.append(attrs)
238
self.o("[")
239
else:
240
self.astack.append(None)
241
else:
242
if self.astack:
243
a = self.astack.pop()
244
if a:
245
i = self.previousIndex(a)
246
if i is not None:
247
a = self.a[i]
248
else:
249
self.acount += 1
250
a['count'] = self.acount
251
a['outcount'] = self.outcount
252
self.a.append(a)
253
self.o("][" + `a['count']` + "]")
254
255
if tag == "img" and start:
256
attrsD = {}
257
for (x, y) in attrs: attrsD[x] = y
258
attrs = attrsD
259
if attrs.has_key('src'):
260
attrs['href'] = attrs['src']
261
alt = attrs.get('alt', '')
262
alt = re.sub('\n', ' ', alt)
263
i = self.previousIndex(attrs)
264
if i is not None:
265
attrs = self.a[i]
266
else:
267
self.acount += 1
268
attrs['count'] = self.acount
269
attrs['outcount'] = self.outcount
270
self.a.append(attrs)
271
self.o("![")
272
self.o(alt)
273
self.o("]["+`attrs['count']`+"]")
274
275
if tag == 'dl' and start: self.p()
276
if tag == 'dt' and not start: self.pbr()
277
if tag == 'dd' and start: self.o(' ')
278
if tag == 'dd' and not start: self.pbr()
279
280
if tag in ["ol", "ul"]:
281
if start:
282
self.list.append({'name':tag, 'num':0})
283
elif self.list:
284
if self.list: self.list.pop()
285
286
self.p()
287
288
if tag == 'li':
289
if start:
290
self.pbr()
291
if self.list: li = self.list[-1]
292
else: li = {'name':'ul', 'num':0}
293
self.o(" "*len(self.list)) #TODO: line up <ol><li>s > 9 correctly.
294
if li['name'] == "ul": self.o("* ")
295
elif li['name'] == "ol":
296
li['num'] += 1
297
self.o(`li['num']`+". ")
298
self.start = 1
299
else:
300
self.pbr()
301
302
if tag in ['tr']: self.pbr()
303
304
if tag == "pre":
305
if start:
306
self.startpre = 1
307
self.pre = 1
308
else:
309
self.pre = 0
310
self.p()
311
312
def pbr(self):
313
if self.p_p == 0: self.p_p = 1
314
315
def p(self): self.p_p = 2
316
317
def o(self, data, puredata=0, force=0):
318
if not self.quiet:
319
if puredata and not self.pre:
320
data = re.sub('\s+', ' ', data)
321
if data and data[0] == ' ':
322
self.space = 1
323
data = data[1:]
324
if not data and not force: return
325
326
if self.startpre:
327
#self.out(" :") #TODO: not output when already one there
328
self.startpre = 0
329
330
bq = (">" * self.blockquote)
331
if not (force and data and data[0] == ">") and self.blockquote: bq += " "
332
333
if self.pre:
334
bq += " "
335
data = data.replace("\n", "\n"+bq)
336
337
if self.start:
338
self.space = 0
339
self.p_p = 0
340
self.start = 0
341
342
if force == 'end':
343
# It's the end.
344
self.p_p = 0
345
self.out("\n")
346
self.space = 0
347
348
349
if self.p_p:
350
self.out(('\n'+bq)*self.p_p)
351
self.space = 0
352
353
if self.space:
354
if not self.lastWasNL: self.out(' ')
355
self.space = 0
356
357
if self.a and ((self.p_p == 2 and LINKS_EACH_PARAGRAPH) or force == "end"):
358
if force == "end": self.out("\n")
359
360
newa = []
361
for link in self.a:
362
if self.outcount > link['outcount']:
363
self.out(" ["+`link['count']`+"]: " + link['href']) #TODO: base href
364
if link.has_key('title'): self.out(" ("+link['title']+")")
365
self.out("\n")
366
else:
367
newa.append(link)
368
369
if self.a != newa: self.out("\n") # Don't need an extra line when nothing was done.
370
371
self.a = newa
372
373
self.p_p = 0
374
self.out(data)
375
self.lastWasNL = data and data[-1] == '\n'
376
self.outcount += 1
377
378
def handle_data(self, data):
379
self.o(data, 1)
380
381
def unknown_decl(self, data): pass
382
383
def html2text_file(html, out=sys.stdout.write):
384
h = _html2text(out)
385
h.feed(html)
386
h.feed("")
387
return h.close()
388
389
def html2text(html):
390
return optwrap(html2text_file(html, None))
391
392
if __name__ == "__main__":
393
if sys.argv[1:]:
394
arg = sys.argv[1]
395
if arg.startswith('http://'):
396
data = urllib.urlopen(arg).read()
397
else:
398
data = open(arg, 'r').read()
399
else:
400
data = sys.stdin.read()
401
html2text_file(data)
402
Loggerhead is a web-based interface for Breezy
Version: 2.0.1