aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/utils.py
blob: 0f903c64a0d8c71517378143ecad1caf07cb5893 (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
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
#!/usr/bin/env python
# -*- coding: utf-8 -*-

import gzip
import htmlentitydefs
import HTMLParser
import locale
import os
import re
import sys
import zlib
import urllib2
import email.utils

try:
	import cStringIO as StringIO
except ImportError:
	import StringIO
		
try:
	import json
except ImportError: # Python <2.6, use trivialjson (https://github.com/phihag/trivialjson):
	import trivialjson as json

std_headers = {
	'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64; rv:5.0.1) Gecko/20100101 Firefox/5.0.1',
	'Accept-Charset': 'ISO-8859-1,utf-8;q=0.7,*;q=0.7',
	'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
	'Accept-Encoding': 'gzip, deflate',
	'Accept-Language': 'en-us,en;q=0.5',
}

def preferredencoding():
	"""Get preferred encoding.

	Returns the best encoding scheme for the system, based on
	locale.getpreferredencoding() and some further tweaks.
	"""
	def yield_preferredencoding():
		try:
			pref = locale.getpreferredencoding()
			u'TEST'.encode(pref)
		except:
			pref = 'UTF-8'
		while True:
			yield pref
	return yield_preferredencoding().next()


def htmlentity_transform(matchobj):
	"""Transforms an HTML entity to a Unicode character.

	This function receives a match object and is intended to be used with
	the re.sub() function.
	"""
	entity = matchobj.group(1)

	# Known non-numeric HTML entity
	if entity in htmlentitydefs.name2codepoint:
		return unichr(htmlentitydefs.name2codepoint[entity])

	# Unicode character
	mobj = re.match(ur'(?u)#(x?\d+)', entity)
	if mobj is not None:
		numstr = mobj.group(1)
		if numstr.startswith(u'x'):
			base = 16
			numstr = u'0%s' % numstr
		else:
			base = 10
		return unichr(long(numstr, base))

	# Unknown entity in name, return its literal representation
	return (u'&%s;' % entity)

HTMLParser.locatestarttagend = re.compile(r"""<[a-zA-Z][-.a-zA-Z0-9:_]*(?:\s+(?:(?<=['"\s])[^\s/>][^\s/=>]*(?:\s*=+\s*(?:'[^']*'|"[^"]*"|(?!['"])[^>\s]*))?\s*)*)?\s*""", re.VERBOSE) # backport bugfix
class IDParser(HTMLParser.HTMLParser):
	"""Modified HTMLParser that isolates a tag with the specified id"""
	def __init__(self, id):
		self.id = id
		self.result = None
		self.started = False
		self.depth = {}
		self.html = None
		self.watch_startpos = False
		self.error_count = 0
		HTMLParser.HTMLParser.__init__(self)

	def error(self, message):
		print self.getpos()
		if self.error_count > 10 or self.started:
			raise HTMLParser.HTMLParseError(message, self.getpos())
		self.rawdata = '\n'.join(self.html.split('\n')[self.getpos()[0]:]) # skip one line
		self.error_count += 1
		self.goahead(1)

	def loads(self, html):
		self.html = html
		self.feed(html)
		self.close()

	def handle_starttag(self, tag, attrs):
		attrs = dict(attrs)
		if self.started:
			self.find_startpos(None)
		if 'id' in attrs and attrs['id'] == self.id:
			self.result = [tag]
			self.started = True
			self.watch_startpos = True
		if self.started:
			if not tag in self.depth: self.depth[tag] = 0
			self.depth[tag] += 1

	def handle_endtag(self, tag):
		if self.started:
			if tag in self.depth: self.depth[tag] -= 1
			if self.depth[self.result[0]] == 0:
				self.started = False
				self.result.append(self.getpos())

	def find_startpos(self, x):
		"""Needed to put the start position of the result (self.result[1])
		after the opening tag with the requested id"""
		if self.watch_startpos:
			self.watch_startpos = False
			self.result.append(self.getpos())
	handle_entityref = handle_charref = handle_data = handle_comment = \
	handle_decl = handle_pi = unknown_decl = find_startpos

	def get_result(self):
		if self.result == None: return None
		if len(self.result) != 3: return None
		lines = self.html.split('\n')
		lines = lines[self.result[1][0]-1:self.result[2][0]]
		lines[0] = lines[0][self.result[1][1]:]
		if len(lines) == 1:
			lines[-1] = lines[-1][:self.result[2][1]-self.result[1][1]]
		lines[-1] = lines[-1][:self.result[2][1]]
		return '\n'.join(lines).strip()

def get_element_by_id(id, html):
	"""Return the content of the tag with the specified id in the passed HTML document"""
	parser = IDParser(id)
	try:
		parser.loads(html)
	except HTMLParser.HTMLParseError:
		pass
	return parser.get_result()


def clean_html(html):
	"""Clean an HTML snippet into a readable string"""
	# Newline vs <br />
	html = html.replace('\n', ' ')
	html = re.sub('\s*<\s*br\s*/?\s*>\s*', '\n', html)
	# Strip html tags
	html = re.sub('<.*?>', '', html)
	# Replace html entities
	html = unescapeHTML(html)
	return html


def sanitize_title(utitle):
	"""Sanitizes a video title so it could be used as part of a filename."""
	utitle = unescapeHTML(utitle)
	return utitle.replace(unicode(os.sep), u'%')


def sanitize_open(filename, open_mode):
	"""Try to open the given filename, and slightly tweak it if this fails.

	Attempts to open the given filename. If this fails, it tries to change
	the filename slightly, step by step, until it's either able to open it
	or it fails and raises a final exception, like the standard open()
	function.

	It returns the tuple (stream, definitive_file_name).
	"""
	try:
		if filename == u'-':
			if sys.platform == 'win32':
				import msvcrt
				msvcrt.setmode(sys.stdout.fileno(), os.O_BINARY)
			return (sys.stdout, filename)
		stream = open(encodeFilename(filename), open_mode)
		return (stream, filename)
	except (IOError, OSError), err:
		# In case of error, try to remove win32 forbidden chars
		filename = re.sub(ur'[/<>:"\|\?\*]', u'#', filename)

		# An exception here should be caught in the caller
		stream = open(encodeFilename(filename), open_mode)
		return (stream, filename)


def timeconvert(timestr):
	"""Convert RFC 2822 defined time string into system timestamp"""
	timestamp = None
	timetuple = email.utils.parsedate_tz(timestr)
	if timetuple is not None:
		timestamp = email.utils.mktime_tz(timetuple)
	return timestamp

def simplify_title(title):
	expr = re.compile(ur'[^\w\d_\-]+', flags=re.UNICODE)
	return expr.sub(u'_', title).strip(u'_')

def orderedSet(iterable):
	""" Remove all duplicates from the input iterable """
	res = []
	for el in iterable:
		if el not in res:
			res.append(el)
	return res

def unescapeHTML(s):
	"""
	@param s a string (of type unicode)
	"""
	assert type(s) == type(u'')

	result = re.sub(ur'(?u)&(.+?);', htmlentity_transform, s)
	return result

def encodeFilename(s):
	"""
	@param s The name of the file (of type unicode)
	"""

	assert type(s) == type(u'')

	if sys.platform == 'win32' and sys.getwindowsversion().major >= 5:
		# Pass u'' directly to use Unicode APIs on Windows 2000 and up
		# (Detecting Windows NT 4 is tricky because 'major >= 4' would
		# match Windows 9x series as well. Besides, NT 4 is obsolete.)
		return s
	else:
		return s.encode(sys.getfilesystemencoding(), 'ignore')

class DownloadError(Exception):
	"""Download Error exception.

	This exception may be thrown by FileDownloader objects if they are not
	configured to continue on errors. They will contain the appropriate
	error message.
	"""
	pass


class SameFileError(Exception):
	"""Same File exception.

	This exception will be thrown by FileDownloader objects if they detect
	multiple files would have to be downloaded to the same file on disk.
	"""
	pass


class PostProcessingError(Exception):
	"""Post Processing exception.

	This exception may be raised by PostProcessor's .run() method to
	indicate an error in the postprocessing task.
	"""
	pass

class MaxDownloadsReached(Exception):
	""" --max-downloads limit has been reached. """
	pass


class UnavailableVideoError(Exception):
	"""Unavailable Format exception.

	This exception will be thrown when a video is requested
	in a format that is not available for that video.
	"""
	pass


class ContentTooShortError(Exception):
	"""Content Too Short exception.

	This exception may be raised by FileDownloader objects when a file they
	download is too small for what the server announced first, indicating
	the connection was probably interrupted.
	"""
	# Both in bytes
	downloaded = None
	expected = None

	def __init__(self, downloaded, expected):
		self.downloaded = downloaded
		self.expected = expected


class YoutubeDLHandler(urllib2.HTTPHandler):
	"""Handler for HTTP requests and responses.

	This class, when installed with an OpenerDirector, automatically adds
	the standard headers to every HTTP request and handles gzipped and
	deflated responses from web servers. If compression is to be avoided in
	a particular request, the original request in the program code only has
	to include the HTTP header "Youtubedl-No-Compression", which will be
	removed before making the real request.

	Part of this code was copied from:

	http://techknack.net/python-urllib2-handlers/

	Andrew Rowls, the author of that code, agreed to release it to the
	public domain.
	"""

	@staticmethod
	def deflate(data):
		try:
			return zlib.decompress(data, -zlib.MAX_WBITS)
		except zlib.error:
			return zlib.decompress(data)

	@staticmethod
	def addinfourl_wrapper(stream, headers, url, code):
		if hasattr(urllib2.addinfourl, 'getcode'):
			return urllib2.addinfourl(stream, headers, url, code)
		ret = urllib2.addinfourl(stream, headers, url)
		ret.code = code
		return ret

	def http_request(self, req):
		for h in std_headers:
			if h in req.headers:
				del req.headers[h]
			req.add_header(h, std_headers[h])
		if 'Youtubedl-no-compression' in req.headers:
			if 'Accept-encoding' in req.headers:
				del req.headers['Accept-encoding']
			del req.headers['Youtubedl-no-compression']
		return req

	def http_response(self, req, resp):
		old_resp = resp
		# gzip
		if resp.headers.get('Content-encoding', '') == 'gzip':
			gz = gzip.GzipFile(fileobj=StringIO.StringIO(resp.read()), mode='r')
			resp = self.addinfourl_wrapper(gz, old_resp.headers, old_resp.url, old_resp.code)
			resp.msg = old_resp.msg
		# deflate
		if resp.headers.get('Content-encoding', '') == 'deflate':
			gz = StringIO.StringIO(self.deflate(resp.read()))
			resp = self.addinfourl_wrapper(gz, old_resp.headers, old_resp.url, old_resp.code)
			resp.msg = old_resp.msg
		return resp