aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/utils.py
blob: 901b5b5ad291686fa653ea39c3d4670d8b7b9dc8 (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
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
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
#!/usr/bin/env python
# -*- coding: utf-8 -*-

import gzip
import io
import json
import locale
import os
import re
import sys
import traceback
import zlib
import email.utils
import json

try:
    import urllib.request as compat_urllib_request
except ImportError: # Python 2
    import urllib2 as compat_urllib_request

try:
    import urllib.error as compat_urllib_error
except ImportError: # Python 2
    import urllib2 as compat_urllib_error

try:
    import urllib.parse as compat_urllib_parse
except ImportError: # Python 2
    import urllib as compat_urllib_parse

try:
    from urllib.parse import urlparse as compat_urllib_parse_urlparse
except ImportError: # Python 2
    from urlparse import urlparse as compat_urllib_parse_urlparse

try:
    import http.cookiejar as compat_cookiejar
except ImportError: # Python 2
    import cookielib as compat_cookiejar

try:
    import html.entities as compat_html_entities
except ImportError: # Python 2
    import htmlentitydefs as compat_html_entities

try:
    import html.parser as compat_html_parser
except ImportError: # Python 2
    import HTMLParser as compat_html_parser

try:
    import http.client as compat_http_client
except ImportError: # Python 2
    import httplib as compat_http_client

try:
    from subprocess import DEVNULL
    compat_subprocess_get_DEVNULL = lambda: DEVNULL
except ImportError:
    compat_subprocess_get_DEVNULL = lambda: open(os.path.devnull, 'w')

try:
    from urllib.parse import parse_qs as compat_parse_qs
except ImportError: # Python 2
    # HACK: The following is the correct parse_qs implementation from cpython 3's stdlib.
    # Python 2's version is apparently totally broken
    def _unquote(string, encoding='utf-8', errors='replace'):
        if string == '':
            return string
        res = string.split('%')
        if len(res) == 1:
            return string
        if encoding is None:
            encoding = 'utf-8'
        if errors is None:
            errors = 'replace'
        # pct_sequence: contiguous sequence of percent-encoded bytes, decoded
        pct_sequence = b''
        string = res[0]
        for item in res[1:]:
            try:
                if not item:
                    raise ValueError
                pct_sequence += item[:2].decode('hex')
                rest = item[2:]
                if not rest:
                    # This segment was just a single percent-encoded character.
                    # May be part of a sequence of code units, so delay decoding.
                    # (Stored in pct_sequence).
                    continue
            except ValueError:
                rest = '%' + item
            # Encountered non-percent-encoded characters. Flush the current
            # pct_sequence.
            string += pct_sequence.decode(encoding, errors) + rest
            pct_sequence = b''
        if pct_sequence:
            # Flush the final pct_sequence
            string += pct_sequence.decode(encoding, errors)
        return string

    def _parse_qsl(qs, keep_blank_values=False, strict_parsing=False,
                encoding='utf-8', errors='replace'):
        qs, _coerce_result = qs, unicode
        pairs = [s2 for s1 in qs.split('&') for s2 in s1.split(';')]
        r = []
        for name_value in pairs:
            if not name_value and not strict_parsing:
                continue
            nv = name_value.split('=', 1)
            if len(nv) != 2:
                if strict_parsing:
                    raise ValueError("bad query field: %r" % (name_value,))
                # Handle case of a control-name with no equal sign
                if keep_blank_values:
                    nv.append('')
                else:
                    continue
            if len(nv[1]) or keep_blank_values:
                name = nv[0].replace('+', ' ')
                name = _unquote(name, encoding=encoding, errors=errors)
                name = _coerce_result(name)
                value = nv[1].replace('+', ' ')
                value = _unquote(value, encoding=encoding, errors=errors)
                value = _coerce_result(value)
                r.append((name, value))
        return r

    def compat_parse_qs(qs, keep_blank_values=False, strict_parsing=False,
                encoding='utf-8', errors='replace'):
        parsed_result = {}
        pairs = _parse_qsl(qs, keep_blank_values, strict_parsing,
                        encoding=encoding, errors=errors)
        for name, value in pairs:
            if name in parsed_result:
                parsed_result[name].append(value)
            else:
                parsed_result[name] = [value]
        return parsed_result

try:
    compat_str = unicode # Python 2
except NameError:
    compat_str = str

try:
    compat_chr = unichr # Python 2
except NameError:
    compat_chr = chr

std_headers = {
    'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64; rv:10.0) Gecko/20100101 Firefox/10.0',
    '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.
    """
    try:
        pref = locale.getpreferredencoding()
        u'TEST'.encode(pref)
    except:
        pref = 'UTF-8'

    return pref

if sys.version_info < (3,0):
    def compat_print(s):
        print(s.encode(preferredencoding(), 'xmlcharrefreplace'))
else:
    def compat_print(s):
        assert type(s) == type(u'')
        print(s)

# In Python 2.x, json.dump expects a bytestream.
# In Python 3.x, it writes to a character stream
if sys.version_info < (3,0):
    def write_json_file(obj, fn):
        with open(fn, 'wb') as f:
            json.dump(obj, f)
else:
    def write_json_file(obj, fn):
        with open(fn, 'w', encoding='utf-8') as f:
            json.dump(obj, f)

def htmlentity_transform(matchobj):
    """Transforms an HTML entity to a 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 compat_html_entities.name2codepoint:
        return compat_chr(compat_html_entities.name2codepoint[entity])

    mobj = re.match(u'(?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 compat_chr(int(numstr, base))

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

compat_html_parser.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 AttrParser(compat_html_parser.HTMLParser):
    """Modified HTMLParser that isolates a tag with the specified attribute"""
    def __init__(self, attribute, value):
        self.attribute = attribute
        self.value = value
        self.result = None
        self.started = False
        self.depth = {}
        self.html = None
        self.watch_startpos = False
        self.error_count = 0
        compat_html_parser.HTMLParser.__init__(self)

    def error(self, message):
        if self.error_count > 10 or self.started:
            raise compat_html_parser.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 self.attribute in attrs and attrs[self.attribute] == self.value:
            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 is 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()
# Hack for https://github.com/rg3/youtube-dl/issues/662
if sys.version_info < (2, 7, 3):
    AttrParser.parse_endtag = (lambda self, i:
        i + len("</scr'+'ipt>")
        if self.rawdata[i:].startswith("</scr'+'ipt>")
        else compat_html_parser.HTMLParser.parse_endtag(self, i))

def get_element_by_id(id, html):
    """Return the content of the tag with the specified ID in the passed HTML document"""
    return get_element_by_attribute("id", id, html)

def get_element_by_attribute(attribute, value, html):
    """Return the content of the tag with the specified attribute in the passed HTML document"""
    parser = AttrParser(attribute, value)
    try:
        parser.loads(html)
    except compat_html_parser.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(r'\s*<\s*br\s*/?\s*>\s*', '\n', html)
    html = re.sub(r'<\s*/\s*p\s*>\s*<\s*p[^>]*>', '\n', html)
    # Strip html tags
    html = re.sub('<.*?>', '', html)
    # Replace html entities
    html = unescapeHTML(html)
    return html


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.buffer, filename)
        stream = open(encodeFilename(filename), open_mode)
        return (stream, filename)
    except (IOError, OSError) as err:
        # In case of error, try to remove win32 forbidden chars
        filename = re.sub(u'[/<>:"\\|\\\\?\\*]', 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 sanitize_filename(s, restricted=False, is_id=False):
    """Sanitizes a string so it could be used as part of a filename.
    If restricted is set, use a stricter subset of allowed characters.
    Set is_id if this is not an arbitrary string, but an ID that should be kept if possible
    """
    def replace_insane(char):
        if char == '?' or ord(char) < 32 or ord(char) == 127:
            return ''
        elif char == '"':
            return '' if restricted else '\''
        elif char == ':':
            return '_-' if restricted else ' -'
        elif char in '\\/|*<>':
            return '_'
        if restricted and (char in '!&\'()[]{}$;`^,#' or char.isspace()):
            return '_'
        if restricted and ord(char) > 127:
            return '_'
        return char

    result = u''.join(map(replace_insane, s))
    if not is_id:
        while '__' in result:
            result = result.replace('__', '_')
        result = result.strip('_')
        # Common case of "Foreign band name - English song title"
        if restricted and result.startswith('-_'):
            result = result[2:]
        if not result:
            result = '_'
    return result

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

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

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

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

    # Python 3 has a Unicode API
    if sys.version_info >= (3, 0):
        return s

    if sys.platform == 'win32' and sys.getwindowsversion()[0] >= 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:
        encoding = sys.getfilesystemencoding()
        if encoding is None:
            encoding = 'utf-8'
        return s.encode(encoding, 'ignore')

def decodeOption(optval):
    if optval is None:
        return optval
    if isinstance(optval, bytes):
        optval = optval.decode(preferredencoding())

    assert isinstance(optval, compat_str)
    return optval

class ExtractorError(Exception):
    """Error during info extraction."""
    def __init__(self, msg, tb=None):
        """ tb, if given, is the original traceback (so that it can be printed out). """
        super(ExtractorError, self).__init__(msg)
        self.traceback = tb

    def format_traceback(self):
        if self.traceback is None:
            return None
        return u''.join(traceback.format_tb(self.traceback))


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.
    """
    def __init__(self, msg):
        self.msg = msg

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(compat_urllib_request.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(compat_urllib_request.addinfourl, 'getcode'):
            return compat_urllib_request.addinfourl(stream, headers, url, code)
        ret = compat_urllib_request.addinfourl(stream, headers, url)
        ret.code = code
        return ret

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

    def http_response(self, req, resp):
        old_resp = resp
        # gzip
        if resp.headers.get('Content-encoding', '') == 'gzip':
            gz = gzip.GzipFile(fileobj=io.BytesIO(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 = io.BytesIO(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

    https_request = http_request
    https_response = http_response