]>
Commit | Line | Data |
---|---|---|
d77c3dfd FV |
1 | #!/usr/bin/env python |
2 | # -*- coding: utf-8 -*- | |
3 | ||
4 | import gzip | |
03f9daab | 5 | import io |
f4bfd65f | 6 | import json |
d77c3dfd FV |
7 | import locale |
8 | import os | |
9 | import re | |
10 | import sys | |
01951dda | 11 | import traceback |
d77c3dfd | 12 | import zlib |
d77c3dfd | 13 | import email.utils |
921a1455 | 14 | import json |
bd558525 | 15 | import datetime |
d77c3dfd | 16 | |
01ba00ca | 17 | try: |
59ae15a5 | 18 | import urllib.request as compat_urllib_request |
01ba00ca | 19 | except ImportError: # Python 2 |
59ae15a5 | 20 | import urllib2 as compat_urllib_request |
01ba00ca PH |
21 | |
22 | try: | |
59ae15a5 | 23 | import urllib.error as compat_urllib_error |
01ba00ca | 24 | except ImportError: # Python 2 |
59ae15a5 | 25 | import urllib2 as compat_urllib_error |
01ba00ca PH |
26 | |
27 | try: | |
59ae15a5 | 28 | import urllib.parse as compat_urllib_parse |
01ba00ca | 29 | except ImportError: # Python 2 |
59ae15a5 | 30 | import urllib as compat_urllib_parse |
01ba00ca | 31 | |
799c0763 PH |
32 | try: |
33 | from urllib.parse import urlparse as compat_urllib_parse_urlparse | |
34 | except ImportError: # Python 2 | |
35 | from urlparse import urlparse as compat_urllib_parse_urlparse | |
36 | ||
01ba00ca | 37 | try: |
59ae15a5 | 38 | import http.cookiejar as compat_cookiejar |
01ba00ca | 39 | except ImportError: # Python 2 |
59ae15a5 | 40 | import cookielib as compat_cookiejar |
01ba00ca | 41 | |
3e669f36 | 42 | try: |
59ae15a5 | 43 | import html.entities as compat_html_entities |
9f37a959 | 44 | except ImportError: # Python 2 |
59ae15a5 | 45 | import htmlentitydefs as compat_html_entities |
3e669f36 | 46 | |
a8156c1d | 47 | try: |
59ae15a5 | 48 | import html.parser as compat_html_parser |
9f37a959 | 49 | except ImportError: # Python 2 |
59ae15a5 | 50 | import HTMLParser as compat_html_parser |
a8156c1d | 51 | |
348d0a7a | 52 | try: |
59ae15a5 | 53 | import http.client as compat_http_client |
9f37a959 | 54 | except ImportError: # Python 2 |
59ae15a5 | 55 | import httplib as compat_http_client |
348d0a7a | 56 | |
5910e210 PH |
57 | try: |
58 | from subprocess import DEVNULL | |
59 | compat_subprocess_get_DEVNULL = lambda: DEVNULL | |
60 | except ImportError: | |
61 | compat_subprocess_get_DEVNULL = lambda: open(os.path.devnull, 'w') | |
62 | ||
9f37a959 | 63 | try: |
59ae15a5 | 64 | from urllib.parse import parse_qs as compat_parse_qs |
9f37a959 | 65 | except ImportError: # Python 2 |
59ae15a5 PH |
66 | # HACK: The following is the correct parse_qs implementation from cpython 3's stdlib. |
67 | # Python 2's version is apparently totally broken | |
68 | def _unquote(string, encoding='utf-8', errors='replace'): | |
69 | if string == '': | |
70 | return string | |
71 | res = string.split('%') | |
72 | if len(res) == 1: | |
73 | return string | |
74 | if encoding is None: | |
75 | encoding = 'utf-8' | |
76 | if errors is None: | |
77 | errors = 'replace' | |
78 | # pct_sequence: contiguous sequence of percent-encoded bytes, decoded | |
79 | pct_sequence = b'' | |
80 | string = res[0] | |
81 | for item in res[1:]: | |
82 | try: | |
83 | if not item: | |
84 | raise ValueError | |
85 | pct_sequence += item[:2].decode('hex') | |
86 | rest = item[2:] | |
87 | if not rest: | |
88 | # This segment was just a single percent-encoded character. | |
89 | # May be part of a sequence of code units, so delay decoding. | |
90 | # (Stored in pct_sequence). | |
91 | continue | |
92 | except ValueError: | |
93 | rest = '%' + item | |
94 | # Encountered non-percent-encoded characters. Flush the current | |
95 | # pct_sequence. | |
96 | string += pct_sequence.decode(encoding, errors) + rest | |
97 | pct_sequence = b'' | |
98 | if pct_sequence: | |
99 | # Flush the final pct_sequence | |
100 | string += pct_sequence.decode(encoding, errors) | |
101 | return string | |
102 | ||
103 | def _parse_qsl(qs, keep_blank_values=False, strict_parsing=False, | |
104 | encoding='utf-8', errors='replace'): | |
105 | qs, _coerce_result = qs, unicode | |
106 | pairs = [s2 for s1 in qs.split('&') for s2 in s1.split(';')] | |
107 | r = [] | |
108 | for name_value in pairs: | |
109 | if not name_value and not strict_parsing: | |
110 | continue | |
111 | nv = name_value.split('=', 1) | |
112 | if len(nv) != 2: | |
113 | if strict_parsing: | |
114 | raise ValueError("bad query field: %r" % (name_value,)) | |
115 | # Handle case of a control-name with no equal sign | |
116 | if keep_blank_values: | |
117 | nv.append('') | |
118 | else: | |
119 | continue | |
120 | if len(nv[1]) or keep_blank_values: | |
121 | name = nv[0].replace('+', ' ') | |
122 | name = _unquote(name, encoding=encoding, errors=errors) | |
123 | name = _coerce_result(name) | |
124 | value = nv[1].replace('+', ' ') | |
125 | value = _unquote(value, encoding=encoding, errors=errors) | |
126 | value = _coerce_result(value) | |
127 | r.append((name, value)) | |
128 | return r | |
129 | ||
130 | def compat_parse_qs(qs, keep_blank_values=False, strict_parsing=False, | |
131 | encoding='utf-8', errors='replace'): | |
132 | parsed_result = {} | |
133 | pairs = _parse_qsl(qs, keep_blank_values, strict_parsing, | |
134 | encoding=encoding, errors=errors) | |
135 | for name, value in pairs: | |
136 | if name in parsed_result: | |
137 | parsed_result[name].append(value) | |
138 | else: | |
139 | parsed_result[name] = [value] | |
140 | return parsed_result | |
348d0a7a | 141 | |
3e669f36 | 142 | try: |
59ae15a5 | 143 | compat_str = unicode # Python 2 |
3e669f36 | 144 | except NameError: |
59ae15a5 | 145 | compat_str = str |
3e669f36 PH |
146 | |
147 | try: | |
59ae15a5 | 148 | compat_chr = unichr # Python 2 |
3e669f36 | 149 | except NameError: |
59ae15a5 | 150 | compat_chr = chr |
3e669f36 | 151 | |
3e669f36 | 152 | std_headers = { |
59ae15a5 PH |
153 | 'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64; rv:10.0) Gecko/20100101 Firefox/10.0', |
154 | 'Accept-Charset': 'ISO-8859-1,utf-8;q=0.7,*;q=0.7', | |
155 | 'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8', | |
156 | 'Accept-Encoding': 'gzip, deflate', | |
157 | 'Accept-Language': 'en-us,en;q=0.5', | |
3e669f36 | 158 | } |
f427df17 | 159 | |
d77c3dfd | 160 | def preferredencoding(): |
59ae15a5 | 161 | """Get preferred encoding. |
d77c3dfd | 162 | |
59ae15a5 PH |
163 | Returns the best encoding scheme for the system, based on |
164 | locale.getpreferredencoding() and some further tweaks. | |
165 | """ | |
166 | try: | |
167 | pref = locale.getpreferredencoding() | |
168 | u'TEST'.encode(pref) | |
169 | except: | |
170 | pref = 'UTF-8' | |
bae611f2 | 171 | |
59ae15a5 | 172 | return pref |
d77c3dfd | 173 | |
8cd10ac4 | 174 | if sys.version_info < (3,0): |
59ae15a5 PH |
175 | def compat_print(s): |
176 | print(s.encode(preferredencoding(), 'xmlcharrefreplace')) | |
8cd10ac4 | 177 | else: |
59ae15a5 PH |
178 | def compat_print(s): |
179 | assert type(s) == type(u'') | |
180 | print(s) | |
d77c3dfd | 181 | |
f4bfd65f PH |
182 | # In Python 2.x, json.dump expects a bytestream. |
183 | # In Python 3.x, it writes to a character stream | |
184 | if sys.version_info < (3,0): | |
185 | def write_json_file(obj, fn): | |
186 | with open(fn, 'wb') as f: | |
187 | json.dump(obj, f) | |
188 | else: | |
189 | def write_json_file(obj, fn): | |
190 | with open(fn, 'w', encoding='utf-8') as f: | |
191 | json.dump(obj, f) | |
192 | ||
d77c3dfd | 193 | def htmlentity_transform(matchobj): |
59ae15a5 PH |
194 | """Transforms an HTML entity to a character. |
195 | ||
196 | This function receives a match object and is intended to be used with | |
197 | the re.sub() function. | |
198 | """ | |
199 | entity = matchobj.group(1) | |
200 | ||
201 | # Known non-numeric HTML entity | |
202 | if entity in compat_html_entities.name2codepoint: | |
203 | return compat_chr(compat_html_entities.name2codepoint[entity]) | |
204 | ||
205 | mobj = re.match(u'(?u)#(x?\\d+)', entity) | |
206 | if mobj is not None: | |
207 | numstr = mobj.group(1) | |
208 | if numstr.startswith(u'x'): | |
209 | base = 16 | |
210 | numstr = u'0%s' % numstr | |
211 | else: | |
212 | base = 10 | |
213 | return compat_chr(int(numstr, base)) | |
214 | ||
215 | # Unknown entity in name, return its literal representation | |
216 | return (u'&%s;' % entity) | |
d77c3dfd | 217 | |
a8156c1d | 218 | 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 |
43e8fafd ND |
219 | class AttrParser(compat_html_parser.HTMLParser): |
220 | """Modified HTMLParser that isolates a tag with the specified attribute""" | |
221 | def __init__(self, attribute, value): | |
222 | self.attribute = attribute | |
223 | self.value = value | |
59ae15a5 PH |
224 | self.result = None |
225 | self.started = False | |
226 | self.depth = {} | |
227 | self.html = None | |
228 | self.watch_startpos = False | |
229 | self.error_count = 0 | |
230 | compat_html_parser.HTMLParser.__init__(self) | |
231 | ||
232 | def error(self, message): | |
233 | if self.error_count > 10 or self.started: | |
234 | raise compat_html_parser.HTMLParseError(message, self.getpos()) | |
235 | self.rawdata = '\n'.join(self.html.split('\n')[self.getpos()[0]:]) # skip one line | |
236 | self.error_count += 1 | |
237 | self.goahead(1) | |
238 | ||
239 | def loads(self, html): | |
240 | self.html = html | |
241 | self.feed(html) | |
242 | self.close() | |
243 | ||
244 | def handle_starttag(self, tag, attrs): | |
245 | attrs = dict(attrs) | |
246 | if self.started: | |
247 | self.find_startpos(None) | |
43e8fafd | 248 | if self.attribute in attrs and attrs[self.attribute] == self.value: |
59ae15a5 PH |
249 | self.result = [tag] |
250 | self.started = True | |
251 | self.watch_startpos = True | |
252 | if self.started: | |
253 | if not tag in self.depth: self.depth[tag] = 0 | |
254 | self.depth[tag] += 1 | |
255 | ||
256 | def handle_endtag(self, tag): | |
257 | if self.started: | |
258 | if tag in self.depth: self.depth[tag] -= 1 | |
259 | if self.depth[self.result[0]] == 0: | |
260 | self.started = False | |
261 | self.result.append(self.getpos()) | |
262 | ||
263 | def find_startpos(self, x): | |
264 | """Needed to put the start position of the result (self.result[1]) | |
265 | after the opening tag with the requested id""" | |
266 | if self.watch_startpos: | |
267 | self.watch_startpos = False | |
268 | self.result.append(self.getpos()) | |
269 | handle_entityref = handle_charref = handle_data = handle_comment = \ | |
270 | handle_decl = handle_pi = unknown_decl = find_startpos | |
271 | ||
272 | def get_result(self): | |
273 | if self.result is None: | |
274 | return None | |
275 | if len(self.result) != 3: | |
276 | return None | |
277 | lines = self.html.split('\n') | |
278 | lines = lines[self.result[1][0]-1:self.result[2][0]] | |
279 | lines[0] = lines[0][self.result[1][1]:] | |
280 | if len(lines) == 1: | |
281 | lines[-1] = lines[-1][:self.result[2][1]-self.result[1][1]] | |
282 | lines[-1] = lines[-1][:self.result[2][1]] | |
283 | return '\n'.join(lines).strip() | |
3b024e17 PH |
284 | # Hack for https://github.com/rg3/youtube-dl/issues/662 |
285 | if sys.version_info < (2, 7, 3): | |
286 | AttrParser.parse_endtag = (lambda self, i: | |
287 | i + len("</scr'+'ipt>") | |
288 | if self.rawdata[i:].startswith("</scr'+'ipt>") | |
289 | else compat_html_parser.HTMLParser.parse_endtag(self, i)) | |
9e6dd238 FV |
290 | |
291 | def get_element_by_id(id, html): | |
43e8fafd ND |
292 | """Return the content of the tag with the specified ID in the passed HTML document""" |
293 | return get_element_by_attribute("id", id, html) | |
294 | ||
295 | def get_element_by_attribute(attribute, value, html): | |
296 | """Return the content of the tag with the specified attribute in the passed HTML document""" | |
297 | parser = AttrParser(attribute, value) | |
59ae15a5 PH |
298 | try: |
299 | parser.loads(html) | |
300 | except compat_html_parser.HTMLParseError: | |
301 | pass | |
302 | return parser.get_result() | |
9e6dd238 FV |
303 | |
304 | ||
305 | def clean_html(html): | |
59ae15a5 PH |
306 | """Clean an HTML snippet into a readable string""" |
307 | # Newline vs <br /> | |
308 | html = html.replace('\n', ' ') | |
6b3aef80 FV |
309 | html = re.sub(r'\s*<\s*br\s*/?\s*>\s*', '\n', html) |
310 | html = re.sub(r'<\s*/\s*p\s*>\s*<\s*p[^>]*>', '\n', html) | |
59ae15a5 PH |
311 | # Strip html tags |
312 | html = re.sub('<.*?>', '', html) | |
313 | # Replace html entities | |
314 | html = unescapeHTML(html) | |
7decf895 | 315 | return html.strip() |
9e6dd238 FV |
316 | |
317 | ||
d77c3dfd | 318 | def sanitize_open(filename, open_mode): |
59ae15a5 PH |
319 | """Try to open the given filename, and slightly tweak it if this fails. |
320 | ||
321 | Attempts to open the given filename. If this fails, it tries to change | |
322 | the filename slightly, step by step, until it's either able to open it | |
323 | or it fails and raises a final exception, like the standard open() | |
324 | function. | |
325 | ||
326 | It returns the tuple (stream, definitive_file_name). | |
327 | """ | |
328 | try: | |
329 | if filename == u'-': | |
330 | if sys.platform == 'win32': | |
331 | import msvcrt | |
332 | msvcrt.setmode(sys.stdout.fileno(), os.O_BINARY) | |
898280a0 | 333 | return (sys.stdout.buffer if hasattr(sys.stdout, 'buffer') else sys.stdout, filename) |
59ae15a5 PH |
334 | stream = open(encodeFilename(filename), open_mode) |
335 | return (stream, filename) | |
336 | except (IOError, OSError) as err: | |
337 | # In case of error, try to remove win32 forbidden chars | |
338 | filename = re.sub(u'[/<>:"\\|\\\\?\\*]', u'#', filename) | |
339 | ||
340 | # An exception here should be caught in the caller | |
341 | stream = open(encodeFilename(filename), open_mode) | |
342 | return (stream, filename) | |
d77c3dfd FV |
343 | |
344 | ||
345 | def timeconvert(timestr): | |
59ae15a5 PH |
346 | """Convert RFC 2822 defined time string into system timestamp""" |
347 | timestamp = None | |
348 | timetuple = email.utils.parsedate_tz(timestr) | |
349 | if timetuple is not None: | |
350 | timestamp = email.utils.mktime_tz(timetuple) | |
351 | return timestamp | |
1c469a94 | 352 | |
796173d0 | 353 | def sanitize_filename(s, restricted=False, is_id=False): |
59ae15a5 PH |
354 | """Sanitizes a string so it could be used as part of a filename. |
355 | If restricted is set, use a stricter subset of allowed characters. | |
796173d0 | 356 | Set is_id if this is not an arbitrary string, but an ID that should be kept if possible |
59ae15a5 PH |
357 | """ |
358 | def replace_insane(char): | |
359 | if char == '?' or ord(char) < 32 or ord(char) == 127: | |
360 | return '' | |
361 | elif char == '"': | |
362 | return '' if restricted else '\'' | |
363 | elif char == ':': | |
364 | return '_-' if restricted else ' -' | |
365 | elif char in '\\/|*<>': | |
366 | return '_' | |
627dcfff | 367 | if restricted and (char in '!&\'()[]{}$;`^,#' or char.isspace()): |
59ae15a5 PH |
368 | return '_' |
369 | if restricted and ord(char) > 127: | |
370 | return '_' | |
371 | return char | |
372 | ||
373 | result = u''.join(map(replace_insane, s)) | |
796173d0 PH |
374 | if not is_id: |
375 | while '__' in result: | |
376 | result = result.replace('__', '_') | |
377 | result = result.strip('_') | |
378 | # Common case of "Foreign band name - English song title" | |
379 | if restricted and result.startswith('-_'): | |
380 | result = result[2:] | |
381 | if not result: | |
382 | result = '_' | |
59ae15a5 | 383 | return result |
d77c3dfd FV |
384 | |
385 | def orderedSet(iterable): | |
59ae15a5 PH |
386 | """ Remove all duplicates from the input iterable """ |
387 | res = [] | |
388 | for el in iterable: | |
389 | if el not in res: | |
390 | res.append(el) | |
391 | return res | |
d77c3dfd FV |
392 | |
393 | def unescapeHTML(s): | |
59ae15a5 PH |
394 | """ |
395 | @param s a string | |
396 | """ | |
397 | assert type(s) == type(u'') | |
d77c3dfd | 398 | |
59ae15a5 PH |
399 | result = re.sub(u'(?u)&(.+?);', htmlentity_transform, s) |
400 | return result | |
d77c3dfd FV |
401 | |
402 | def encodeFilename(s): | |
59ae15a5 PH |
403 | """ |
404 | @param s The name of the file | |
405 | """ | |
d77c3dfd | 406 | |
59ae15a5 | 407 | assert type(s) == type(u'') |
d77c3dfd | 408 | |
59ae15a5 PH |
409 | # Python 3 has a Unicode API |
410 | if sys.version_info >= (3, 0): | |
411 | return s | |
0f00efed | 412 | |
59ae15a5 PH |
413 | if sys.platform == 'win32' and sys.getwindowsversion()[0] >= 5: |
414 | # Pass u'' directly to use Unicode APIs on Windows 2000 and up | |
415 | # (Detecting Windows NT 4 is tricky because 'major >= 4' would | |
416 | # match Windows 9x series as well. Besides, NT 4 is obsolete.) | |
417 | return s | |
418 | else: | |
6df40dcb PH |
419 | encoding = sys.getfilesystemencoding() |
420 | if encoding is None: | |
421 | encoding = 'utf-8' | |
422 | return s.encode(encoding, 'ignore') | |
d77c3dfd | 423 | |
8271226a PH |
424 | def decodeOption(optval): |
425 | if optval is None: | |
426 | return optval | |
427 | if isinstance(optval, bytes): | |
428 | optval = optval.decode(preferredencoding()) | |
429 | ||
430 | assert isinstance(optval, compat_str) | |
431 | return optval | |
1c256f70 | 432 | |
4539dd30 PH |
433 | def formatSeconds(secs): |
434 | if secs > 3600: | |
435 | return '%d:%02d:%02d' % (secs // 3600, (secs % 3600) // 60, secs % 60) | |
436 | elif secs > 60: | |
437 | return '%d:%02d' % (secs // 60, secs % 60) | |
438 | else: | |
439 | return '%d' % secs | |
440 | ||
ea6d901e PH |
441 | def make_HTTPS_handler(opts): |
442 | if sys.version_info < (3,2): | |
443 | # Python's 2.x handler is very simplistic | |
444 | return compat_urllib_request.HTTPSHandler() | |
445 | else: | |
446 | import ssl | |
447 | context = ssl.SSLContext(ssl.PROTOCOL_SSLv23) | |
448 | context.set_default_verify_paths() | |
449 | ||
450 | context.verify_mode = (ssl.CERT_NONE | |
451 | if opts.no_check_certificate | |
452 | else ssl.CERT_REQUIRED) | |
453 | return compat_urllib_request.HTTPSHandler(context=context) | |
454 | ||
1c256f70 PH |
455 | class ExtractorError(Exception): |
456 | """Error during info extraction.""" | |
457 | def __init__(self, msg, tb=None): | |
01951dda | 458 | """ tb, if given, is the original traceback (so that it can be printed out). """ |
1c256f70 | 459 | super(ExtractorError, self).__init__(msg) |
1c256f70 | 460 | self.traceback = tb |
8cc83b8d | 461 | self.exc_info = sys.exc_info() # preserve original exception |
1c256f70 | 462 | |
01951dda PH |
463 | def format_traceback(self): |
464 | if self.traceback is None: | |
465 | return None | |
466 | return u''.join(traceback.format_tb(self.traceback)) | |
467 | ||
1c256f70 | 468 | |
d77c3dfd | 469 | class DownloadError(Exception): |
59ae15a5 | 470 | """Download Error exception. |
d77c3dfd | 471 | |
59ae15a5 PH |
472 | This exception may be thrown by FileDownloader objects if they are not |
473 | configured to continue on errors. They will contain the appropriate | |
474 | error message. | |
475 | """ | |
8cc83b8d FV |
476 | def __init__(self, msg, exc_info=None): |
477 | """ exc_info, if given, is the original exception that caused the trouble (as returned by sys.exc_info()). """ | |
478 | super(DownloadError, self).__init__(msg) | |
479 | self.exc_info = exc_info | |
d77c3dfd FV |
480 | |
481 | ||
482 | class SameFileError(Exception): | |
59ae15a5 | 483 | """Same File exception. |
d77c3dfd | 484 | |
59ae15a5 PH |
485 | This exception will be thrown by FileDownloader objects if they detect |
486 | multiple files would have to be downloaded to the same file on disk. | |
487 | """ | |
488 | pass | |
d77c3dfd FV |
489 | |
490 | ||
491 | class PostProcessingError(Exception): | |
59ae15a5 | 492 | """Post Processing exception. |
d77c3dfd | 493 | |
59ae15a5 PH |
494 | This exception may be raised by PostProcessor's .run() method to |
495 | indicate an error in the postprocessing task. | |
496 | """ | |
7851b379 PH |
497 | def __init__(self, msg): |
498 | self.msg = msg | |
d77c3dfd FV |
499 | |
500 | class MaxDownloadsReached(Exception): | |
59ae15a5 PH |
501 | """ --max-downloads limit has been reached. """ |
502 | pass | |
d77c3dfd FV |
503 | |
504 | ||
505 | class UnavailableVideoError(Exception): | |
59ae15a5 | 506 | """Unavailable Format exception. |
d77c3dfd | 507 | |
59ae15a5 PH |
508 | This exception will be thrown when a video is requested |
509 | in a format that is not available for that video. | |
510 | """ | |
511 | pass | |
d77c3dfd FV |
512 | |
513 | ||
514 | class ContentTooShortError(Exception): | |
59ae15a5 | 515 | """Content Too Short exception. |
d77c3dfd | 516 | |
59ae15a5 PH |
517 | This exception may be raised by FileDownloader objects when a file they |
518 | download is too small for what the server announced first, indicating | |
519 | the connection was probably interrupted. | |
520 | """ | |
521 | # Both in bytes | |
522 | downloaded = None | |
523 | expected = None | |
d77c3dfd | 524 | |
59ae15a5 PH |
525 | def __init__(self, downloaded, expected): |
526 | self.downloaded = downloaded | |
527 | self.expected = expected | |
d77c3dfd | 528 | |
01ba00ca | 529 | class YoutubeDLHandler(compat_urllib_request.HTTPHandler): |
59ae15a5 PH |
530 | """Handler for HTTP requests and responses. |
531 | ||
532 | This class, when installed with an OpenerDirector, automatically adds | |
533 | the standard headers to every HTTP request and handles gzipped and | |
534 | deflated responses from web servers. If compression is to be avoided in | |
535 | a particular request, the original request in the program code only has | |
536 | to include the HTTP header "Youtubedl-No-Compression", which will be | |
537 | removed before making the real request. | |
538 | ||
539 | Part of this code was copied from: | |
540 | ||
541 | http://techknack.net/python-urllib2-handlers/ | |
542 | ||
543 | Andrew Rowls, the author of that code, agreed to release it to the | |
544 | public domain. | |
545 | """ | |
546 | ||
547 | @staticmethod | |
548 | def deflate(data): | |
549 | try: | |
550 | return zlib.decompress(data, -zlib.MAX_WBITS) | |
551 | except zlib.error: | |
552 | return zlib.decompress(data) | |
553 | ||
554 | @staticmethod | |
555 | def addinfourl_wrapper(stream, headers, url, code): | |
556 | if hasattr(compat_urllib_request.addinfourl, 'getcode'): | |
557 | return compat_urllib_request.addinfourl(stream, headers, url, code) | |
558 | ret = compat_urllib_request.addinfourl(stream, headers, url) | |
559 | ret.code = code | |
560 | return ret | |
561 | ||
562 | def http_request(self, req): | |
335959e7 | 563 | for h,v in std_headers.items(): |
59ae15a5 PH |
564 | if h in req.headers: |
565 | del req.headers[h] | |
335959e7 | 566 | req.add_header(h, v) |
59ae15a5 PH |
567 | if 'Youtubedl-no-compression' in req.headers: |
568 | if 'Accept-encoding' in req.headers: | |
569 | del req.headers['Accept-encoding'] | |
570 | del req.headers['Youtubedl-no-compression'] | |
3446dfb7 | 571 | if 'Youtubedl-user-agent' in req.headers: |
335959e7 PH |
572 | if 'User-agent' in req.headers: |
573 | del req.headers['User-agent'] | |
574 | req.headers['User-agent'] = req.headers['Youtubedl-user-agent'] | |
3446dfb7 | 575 | del req.headers['Youtubedl-user-agent'] |
59ae15a5 PH |
576 | return req |
577 | ||
578 | def http_response(self, req, resp): | |
579 | old_resp = resp | |
580 | # gzip | |
581 | if resp.headers.get('Content-encoding', '') == 'gzip': | |
582 | gz = gzip.GzipFile(fileobj=io.BytesIO(resp.read()), mode='r') | |
583 | resp = self.addinfourl_wrapper(gz, old_resp.headers, old_resp.url, old_resp.code) | |
584 | resp.msg = old_resp.msg | |
585 | # deflate | |
586 | if resp.headers.get('Content-encoding', '') == 'deflate': | |
587 | gz = io.BytesIO(self.deflate(resp.read())) | |
588 | resp = self.addinfourl_wrapper(gz, old_resp.headers, old_resp.url, old_resp.code) | |
589 | resp.msg = old_resp.msg | |
590 | return resp | |
0f8d03f8 PH |
591 | |
592 | https_request = http_request | |
593 | https_response = http_response | |
bf50b038 JMF |
594 | |
595 | def unified_strdate(date_str): | |
596 | """Return a string with the date in the format YYYYMMDD""" | |
597 | upload_date = None | |
598 | #Replace commas | |
599 | date_str = date_str.replace(',',' ') | |
600 | # %z (UTC offset) is only supported in python>=3.2 | |
601 | date_str = re.sub(r' (\+|-)[\d]*$', '', date_str) | |
602 | format_expressions = ['%d %B %Y', '%B %d %Y', '%b %d %Y', '%Y-%m-%d', '%d/%m/%Y', '%Y/%m/%d %H:%M:%S'] | |
603 | for expression in format_expressions: | |
604 | try: | |
605 | upload_date = datetime.datetime.strptime(date_str, expression).strftime('%Y%m%d') | |
606 | except: | |
607 | pass | |
608 | return upload_date | |
609 | ||
bd558525 | 610 | def date_from_str(date_str): |
37254abc JMF |
611 | """ |
612 | Return a datetime object from a string in the format YYYYMMDD or | |
613 | (now|today)[+-][0-9](day|week|month|year)(s)?""" | |
614 | today = datetime.date.today() | |
615 | if date_str == 'now'or date_str == 'today': | |
616 | return today | |
617 | match = re.match('(now|today)(?P<sign>[+-])(?P<time>\d+)(?P<unit>day|week|month|year)(s)?', date_str) | |
618 | if match is not None: | |
619 | sign = match.group('sign') | |
620 | time = int(match.group('time')) | |
621 | if sign == '-': | |
622 | time = -time | |
623 | unit = match.group('unit') | |
624 | #A bad aproximation? | |
625 | if unit == 'month': | |
626 | unit = 'day' | |
627 | time *= 30 | |
628 | elif unit == 'year': | |
629 | unit = 'day' | |
630 | time *= 365 | |
631 | unit += 's' | |
632 | delta = datetime.timedelta(**{unit: time}) | |
633 | return today + delta | |
bd558525 JMF |
634 | return datetime.datetime.strptime(date_str, "%Y%m%d").date() |
635 | ||
636 | class DateRange(object): | |
637 | """Represents a time interval between two dates""" | |
638 | def __init__(self, start=None, end=None): | |
639 | """start and end must be strings in the format accepted by date""" | |
640 | if start is not None: | |
641 | self.start = date_from_str(start) | |
642 | else: | |
643 | self.start = datetime.datetime.min.date() | |
644 | if end is not None: | |
645 | self.end = date_from_str(end) | |
646 | else: | |
647 | self.end = datetime.datetime.max.date() | |
37254abc | 648 | if self.start > self.end: |
bd558525 JMF |
649 | raise ValueError('Date range: "%s" , the start date must be before the end date' % self) |
650 | @classmethod | |
651 | def day(cls, day): | |
652 | """Returns a range that only contains the given day""" | |
653 | return cls(day,day) | |
654 | def __contains__(self, date): | |
655 | """Check if the date is in the range""" | |
37254abc JMF |
656 | if not isinstance(date, datetime.date): |
657 | date = date_from_str(date) | |
658 | return self.start <= date <= self.end | |
bd558525 JMF |
659 | def __str__(self): |
660 | return '%s - %s' % ( self.start.isoformat(), self.end.isoformat()) |