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
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
|
"""html2text: Turn HTML into equivalent Markdown-structured text."""
__version__ = "2.28"
__author__ = "Aaron Swartz (me@aaronsw.com)"
__copyright__ = "(C) 2004-2007 Aaron Swartz. GNU GPL 2."
__contributors__ = ["Martin 'Joey' Schulze", "Ricardo Reyes"]
# TODO:
# Support decoded entities with unifiable.
# Relative URL resolution
if not hasattr(__builtins__, 'True'): True, False = 1, 0
import re, sys, urllib, htmlentitydefs, codecs, StringIO, types
import sgmllib
sgmllib.charref = re.compile('&#([xX]?[0-9a-fA-F]+)[^0-9a-fA-F]')
try: from textwrap import wrap
except: pass
# Use Unicode characters instead of their ascii psuedo-replacements
UNICODE_SNOB = 0
# Put the links after each paragraph instead of at the end.
LINKS_EACH_PARAGRAPH = 0
# Wrap long lines at position. 0 for no wrapping. (Requires Python 2.3.)
BODY_WIDTH = 0
### Entity Nonsense ###
def name2cp(k):
if k == 'apos': return ord("'")
if hasattr(htmlentitydefs, "name2codepoint"): # requires Python 2.3
return htmlentitydefs.name2codepoint[k]
else:
k = htmlentitydefs.entitydefs[k]
if k.startswith("&#") and k.endswith(";"): return int(k[2:-1]) # not in latin-1
return ord(codecs.latin_1_decode(k)[0])
unifiable = {'rsquo':"'", 'lsquo':"'", 'rdquo':'"', 'ldquo':'"',
'copy':'(C)', 'mdash':'--', 'nbsp':' ', 'rarr':'->', 'larr':'<-', 'middot':'*',
'ndash':'-', 'oelig':'oe', 'aelig':'ae',
'agrave':'a', 'aacute':'a', 'acirc':'a', 'atilde':'a', 'auml':'a', 'aring':'a',
'egrave':'e', 'eacute':'e', 'ecirc':'e', 'euml':'e',
'igrave':'i', 'iacute':'i', 'icirc':'i', 'iuml':'i',
'ograve':'o', 'oacute':'o', 'ocirc':'o', 'otilde':'o', 'ouml':'o',
'ugrave':'u', 'uacute':'u', 'ucirc':'u', 'uuml':'u'}
unifiable_n = {}
for k in unifiable.keys():
unifiable_n[name2cp(k)] = unifiable[k]
def charref(name):
if name[0] in ['x','X']:
c = int(name[1:], 16)
else:
c = int(name)
if not UNICODE_SNOB and c in unifiable_n.keys():
return unifiable_n[c]
else:
return unichr(c)
def entityref(c):
if not UNICODE_SNOB and c in unifiable.keys():
return unifiable[c]
else:
try: name2cp(c)
except KeyError: return "&" + c
else: return unichr(name2cp(c))
def replaceEntities(s):
s = s.group(1)
if s[0] == "#":
return charref(s[1:])
else: return entityref(s)
r_unescape = re.compile(r"&(#?[xX]?(?:[0-9a-fA-F]+|\w{1,8}));")
def unescape(s):
return r_unescape.sub(replaceEntities, s)
def fixattrs(attrs):
# Fix bug in sgmllib.py
if not attrs: return attrs
newattrs = []
for attr in attrs:
newattrs.append((attr[0], unescape(attr[1])))
return newattrs
### End Entity Nonsense ###
def onlywhite(line):
"""Return true if the line does only consist of whitespace characters."""
for c in line:
if c is not ' ' and c is not ' ':
return c is ' '
return line
def optwrap(text):
"""Wrap all paragraphs in the provided text."""
if not BODY_WIDTH:
return text
assert wrap # Requires Python 2.3.
result = ''
newlines = 0
for para in text.split("\n"):
if len(para) > 0:
if para[0] is not ' ' and para[0] is not '-' and para[0] is not '*':
for line in wrap(para, BODY_WIDTH):
result += line + "\n"
result += "\n"
newlines = 2
else:
if not onlywhite(para):
result += para + "\n"
newlines = 1
else:
if newlines < 2:
result += "\n"
newlines += 1
return result
def hn(tag):
if tag[0] == 'h' and len(tag) == 2:
try:
n = int(tag[1])
if n in range(1, 10): return n
except ValueError: return 0
class _html2text(sgmllib.SGMLParser):
def __init__(self, out=sys.stdout.write):
sgmllib.SGMLParser.__init__(self)
if out is None: self.out = self.outtextf
else: self.out = out
self.outtext = u''
self.quiet = 0
self.p_p = 0
self.outcount = 0
self.start = 1
self.space = 0
self.a = []
self.astack = []
self.acount = 0
self.list = []
self.blockquote = 0
self.pre = 0
self.startpre = 0
self.lastWasNL = 0
def outtextf(self, s):
if type(s) is type(''): s = codecs.utf_8_decode(s)[0]
self.outtext += s
def close(self):
sgmllib.SGMLParser.close(self)
self.pbr()
self.o('', 0, 'end')
return self.outtext
def handle_charref(self, c):
self.o(charref(c))
def handle_entityref(self, c):
self.o(entityref(c))
def unknown_starttag(self, tag, attrs):
self.handle_tag(tag, attrs, 1)
def unknown_endtag(self, tag):
self.handle_tag(tag, None, 0)
def previousIndex(self, attrs):
""" returns the index of certain set of attributes (of a link) in the
self.a list
If the set of attributes is not found, returns None
"""
if not attrs.has_key('href'): return None
i = -1
for a in self.a:
i += 1
match = 0
if a.has_key('href') and a['href'] == attrs['href']:
if a.has_key('title') or attrs.has_key('title'):
if (a.has_key('title') and attrs.has_key('title') and
a['title'] == attrs['title']):
match = True
else:
match = True
if match: return i
def handle_tag(self, tag, attrs, start):
attrs = fixattrs(attrs)
if hn(tag):
self.p()
if start: self.o(hn(tag)*"#" + ' ')
if tag in ['p', 'div']: self.p()
if tag == "br" and start: self.o(" \n")
if tag == "hr" and start:
self.p()
self.o("* * *")
self.p()
if tag in ["head", "style", 'script']:
if start: self.quiet += 1
else: self.quiet -= 1
if tag == "blockquote":
if start:
self.p(); self.o('> ', 0, 1); self.start = 1
self.blockquote += 1
else:
self.blockquote -= 1
self.p()
if tag in ['em', 'i', 'u']: self.o("_")
if tag in ['strong', 'b']: self.o("**")
if tag == "code" and not self.pre: self.o('`') #TODO: `` `this` ``
if tag == "a":
if start:
attrsD = {}
for (x, y) in attrs: attrsD[x] = y
attrs = attrsD
if attrs.has_key('href'):
self.astack.append(attrs)
self.o("[")
else:
self.astack.append(None)
else:
if self.astack:
a = self.astack.pop()
if a:
i = self.previousIndex(a)
if i is not None:
a = self.a[i]
else:
self.acount += 1
a['count'] = self.acount
a['outcount'] = self.outcount
self.a.append(a)
self.o("][" + `a['count']` + "]")
if tag == "img" and start:
attrsD = {}
for (x, y) in attrs: attrsD[x] = y
attrs = attrsD
if attrs.has_key('src'):
attrs['href'] = attrs['src']
alt = attrs.get('alt', '')
i = self.previousIndex(attrs)
if i is not None:
attrs = self.a[i]
else:
self.acount += 1
attrs['count'] = self.acount
attrs['outcount'] = self.outcount
self.a.append(attrs)
self.o("![")
self.o(alt)
self.o("]["+`attrs['count']`+"]")
if tag == 'dl' and start: self.p()
if tag == 'dt' and not start: self.pbr()
if tag == 'dd' and start: self.o(' ')
if tag == 'dd' and not start: self.pbr()
if tag in ["ol", "ul"]:
if start:
self.list.append({'name':tag, 'num':0})
else:
if self.list: self.list.pop()
self.p()
if tag == 'li':
if start:
self.pbr()
if self.list: li = self.list[-1]
else: li = {'name':'ul', 'num':0}
self.o(" "*len(self.list)) #TODO: line up <ol><li>s > 9 correctly.
if li['name'] == "ul": self.o("* ")
elif li['name'] == "ol":
li['num'] += 1
self.o(`li['num']`+". ")
self.start = 1
else:
self.pbr()
if tag in ["table", "tr"] and start: self.p()
if tag == 'td': self.pbr()
if tag == "pre":
if start:
self.startpre = 1
self.pre = 1
else:
self.pre = 0
self.p()
def pbr(self):
if self.p_p == 0: self.p_p = 1
def p(self): self.p_p = 2
def o(self, data, puredata=0, force=0):
if not self.quiet:
if puredata and not self.pre:
data = re.sub('\s+', ' ', data)
if data and data[0] == ' ':
self.space = 1
data = data[1:]
if not data and not force: return
if self.startpre:
#self.out(" :") #TODO: not output when already one there
self.startpre = 0
bq = (">" * self.blockquote)
if not (force and data and data[0] == ">") and self.blockquote: bq += " "
if self.pre:
bq += " "
data = data.replace("\n", "\n"+bq)
if self.start:
self.space = 0
self.p_p = 0
self.start = 0
if force == 'end':
# It's the end.
self.p_p = 0
self.out("\n")
self.space = 0
if self.p_p:
self.out(('\n'+bq)*self.p_p)
self.space = 0
if self.space:
if not self.lastWasNL: self.out(' ')
self.space = 0
if self.a and ((self.p_p == 2 and LINKS_EACH_PARAGRAPH) or force == "end"):
if force == "end": self.out("\n")
newa = []
for link in self.a:
if self.outcount > link['outcount']:
self.out(" ["+`link['count']`+"]: " + link['href']) #TODO: base href
if link.has_key('title'): self.out(" ("+link['title']+")")
self.out("\n")
else:
newa.append(link)
if self.a != newa: self.out("\n") # Don't need an extra line when nothing was done.
self.a = newa
self.p_p = 0
self.out(data)
self.lastWasNL = data and data[-1] == '\n'
self.outcount += 1
def handle_data(self, data):
self.o(data, 1)
def unknown_decl(self, data): pass
def wrapwrite(text): sys.stdout.write(text.encode('utf8'))
def html2text_file(html, out=wrapwrite):
h = _html2text(out)
h.feed(html)
h.feed("")
return h.close()
def html2text(html):
return optwrap(html2text_file(html, None))
if __name__ == "__main__":
if sys.argv[1:]:
arg = sys.argv[1]
if arg.startswith('http://'):
j = urllib.urlopen(arg)
try:
from feedparser import _getCharacterEncoding as enc
except ImportError:
enc = lambda x, y: y, x
text = j.read()
encoding = enc(j.headers, text)[0]
if encoding == 'us-ascii': encoding = 'utf-8'
data = html2text_file(text.decode(encoding))
else:
data = open(arg, 'r').read()
else:
data = sys.stdin.read()
html2text_file(data) |
