]>
Commit | Line | Data |
---|---|---|
cb3bb2cf PH |
1 | from __future__ import unicode_literals |
2 | ||
9eae41dd PH |
3 | import re |
4 | import socket | |
5 | ||
6 | from .common import InfoExtractor | |
8c25f81b | 7 | from ..compat import ( |
0803753f | 8 | compat_etree_fromstring, |
9eae41dd | 9 | compat_http_client, |
9eae41dd | 10 | compat_urllib_error, |
d7011316 | 11 | compat_urllib_parse_unquote, |
0803753f | 12 | compat_urllib_parse_unquote_plus, |
8c25f81b PH |
13 | ) |
14 | from ..utils import ( | |
b83ef507 | 15 | clean_html, |
9b9c5355 | 16 | error_to_compat_str, |
9eae41dd | 17 | ExtractorError, |
b83ef507 | 18 | get_element_by_id, |
196c6ba0 | 19 | int_or_none, |
b83ef507 | 20 | js_to_json, |
a020a0dc | 21 | limit_length, |
5c2266df | 22 | sanitized_Request, |
b83ef507 | 23 | try_get, |
2fc9f2b4 | 24 | urlencode_postdata, |
9eae41dd PH |
25 | ) |
26 | ||
27 | ||
28 | class FacebookIE(InfoExtractor): | |
9834872b | 29 | _VALID_URL = r'''(?x) |
2e6e742c S |
30 | (?: |
31 | https?:// | |
30918999 | 32 | (?:[\w-]+\.)?(?:facebook\.com|facebookcorewwwi\.onion)/ |
2e6e742c S |
33 | (?:[^#]*?\#!/)? |
34 | (?: | |
35 | (?: | |
36 | video/video\.php| | |
37 | photo\.php| | |
38 | video\.php| | |
efbeddea YCH |
39 | video/embed| |
40 | story\.php | |
41 | )\?(?:.*?)(?:v|video_id|story_fbid)=| | |
9c7b509b | 42 | [^/]+/videos/(?:[^/]+/)?| |
e738e433 YCH |
43 | [^/]+/posts/| |
44 | groups/[^/]+/permalink/ | |
2e6e742c S |
45 | )| |
46 | facebook: | |
47 | ) | |
48 | (?P<id>[0-9]+) | |
49 | ''' | |
67874aef JMF |
50 | _LOGIN_URL = 'https://www.facebook.com/login.php?next=http%3A%2F%2Ffacebook.com%2Fhome.php&login_attempt=1' |
51 | _CHECKPOINT_URL = 'https://www.facebook.com/checkpoint/?next=http%3A%2F%2Ffacebook.com%2Fhome.php&_fb_noscript=1' | |
9eae41dd | 52 | _NETRC_MACHINE = 'facebook' |
cb3bb2cf | 53 | IE_NAME = 'facebook' |
0803753f YCH |
54 | |
55 | _CHROME_USER_AGENT = 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/48.0.2564.97 Safari/537.36' | |
56 | ||
9c7b509b YCH |
57 | _VIDEO_PAGE_TEMPLATE = 'https://www.facebook.com/video/video.php?v=%s' |
58 | ||
60ac04e5 | 59 | _TESTS = [{ |
50317dbb PH |
60 | 'url': 'https://www.facebook.com/video.php?v=637842556329505&fref=nf', |
61 | 'md5': '6a40d33c0eccbb1af76cf0485a052659', | |
cb3bb2cf | 62 | 'info_dict': { |
50317dbb | 63 | 'id': '637842556329505', |
cb3bb2cf | 64 | 'ext': 'mp4', |
5e4f0619 | 65 | 'title': 're:Did you know Kei Nishikori is the first Asian man to ever reach a Grand Slam', |
67b8a28a | 66 | 'uploader': 'Tennis on Facebook', |
196c6ba0 S |
67 | 'upload_date': '20140908', |
68 | 'timestamp': 1410199200, | |
6f5ac90c | 69 | } |
a020a0dc PH |
70 | }, { |
71 | 'note': 'Video without discernible title', | |
72 | 'url': 'https://www.facebook.com/video.php?v=274175099429670', | |
73 | 'info_dict': { | |
74 | 'id': '274175099429670', | |
75 | 'ext': 'mp4', | |
5a116e13 | 76 | 'title': 'Asif Nawab Butt posted a video to his Timeline.', |
67b8a28a | 77 | 'uploader': 'Asif Nawab Butt', |
196c6ba0 S |
78 | 'upload_date': '20140506', |
79 | 'timestamp': 1399398998, | |
db3ca364 YCH |
80 | }, |
81 | 'expected_warnings': [ | |
82 | 'title' | |
83 | ] | |
0803753f YCH |
84 | }, { |
85 | 'note': 'Video with DASH manifest', | |
86 | 'url': 'https://www.facebook.com/video.php?v=957955867617029', | |
196c6ba0 | 87 | 'md5': 'b2c28d528273b323abe5c6ab59f0f030', |
0803753f YCH |
88 | 'info_dict': { |
89 | 'id': '957955867617029', | |
90 | 'ext': 'mp4', | |
91 | 'title': 'When you post epic content on instagram.com/433 8 million followers, this is ...', | |
92 | 'uploader': 'Demy de Zeeuw', | |
196c6ba0 S |
93 | 'upload_date': '20160110', |
94 | 'timestamp': 1452431627, | |
0803753f | 95 | }, |
9c7b509b YCH |
96 | }, { |
97 | 'url': 'https://www.facebook.com/maxlayn/posts/10153807558977570', | |
98 | 'md5': '037b1fa7f3c2d02b7a0d7bc16031ecc6', | |
99 | 'info_dict': { | |
100 | 'id': '544765982287235', | |
101 | 'ext': 'mp4', | |
102 | 'title': '"What are you doing running in the snow?"', | |
103 | 'uploader': 'FailArmy', | |
d9ee2e5c YCH |
104 | }, |
105 | 'skip': 'Video gone', | |
98801241 YCH |
106 | }, { |
107 | 'url': 'https://m.facebook.com/story.php?story_fbid=1035862816472149&id=116132035111903', | |
108 | 'md5': '1deb90b6ac27f7efcf6d747c8a27f5e3', | |
109 | 'info_dict': { | |
110 | 'id': '1035862816472149', | |
111 | 'ext': 'mp4', | |
112 | 'title': 'What the Flock Is Going On In New Zealand Credit: ViralHog', | |
113 | 'uploader': 'S. Saint', | |
114 | }, | |
d9ee2e5c | 115 | 'skip': 'Video gone', |
5080cbf9 YCH |
116 | }, { |
117 | 'note': 'swf params escaped', | |
118 | 'url': 'https://www.facebook.com/barackobama/posts/10153664894881749', | |
119 | 'md5': '97ba073838964d12c70566e0085c2b91', | |
120 | 'info_dict': { | |
121 | 'id': '10153664894881749', | |
122 | 'ext': 'mp4', | |
123 | 'title': 'Facebook video #10153664894881749', | |
124 | }, | |
d9ee2e5c YCH |
125 | }, { |
126 | # have 1080P, but only up to 720p in swf params | |
127 | 'url': 'https://www.facebook.com/cnn/videos/10155529876156509/', | |
128 | 'md5': '0d9813160b146b3bc8744e006027fcc6', | |
129 | 'info_dict': { | |
130 | 'id': '10155529876156509', | |
131 | 'ext': 'mp4', | |
132 | 'title': 'Holocaust survivor becomes US citizen', | |
133 | 'timestamp': 1477818095, | |
134 | 'upload_date': '20161030', | |
135 | 'uploader': 'CNN', | |
136 | }, | |
60ac04e5 PH |
137 | }, { |
138 | 'url': 'https://www.facebook.com/video.php?v=10204634152394104', | |
139 | 'only_matching': True, | |
c6256697 YCH |
140 | }, { |
141 | 'url': 'https://www.facebook.com/amogood/videos/1618742068337349/?fref=nf', | |
142 | 'only_matching': True, | |
53faa3ca YCH |
143 | }, { |
144 | 'url': 'https://www.facebook.com/ChristyClarkForBC/videos/vb.22819070941/10153870694020942/?type=2&theater', | |
145 | 'only_matching': True, | |
2e6e742c S |
146 | }, { |
147 | 'url': 'facebook:544765982287235', | |
148 | 'only_matching': True, | |
e738e433 YCH |
149 | }, { |
150 | 'url': 'https://www.facebook.com/groups/164828000315060/permalink/764967300301124/', | |
151 | 'only_matching': True, | |
b4a131e1 S |
152 | }, { |
153 | 'url': 'https://zh-hk.facebook.com/peoplespower/videos/1135894589806027/', | |
154 | 'only_matching': True, | |
30918999 YCH |
155 | }, { |
156 | 'url': 'https://www.facebookcorewwwi.onion/video.php?v=274175099429670', | |
157 | 'only_matching': True, | |
60ac04e5 | 158 | }] |
9eae41dd | 159 | |
fd6ca382 YCH |
160 | @staticmethod |
161 | def _extract_url(webpage): | |
162 | mobj = re.search( | |
163 | r'<iframe[^>]+?src=(["\'])(?P<url>https://www\.facebook\.com/video/embed.+?)\1', webpage) | |
164 | if mobj is not None: | |
165 | return mobj.group('url') | |
166 | ||
167 | # Facebook API embed | |
168 | # see https://developers.facebook.com/docs/plugins/embedded-video-player | |
169 | mobj = re.search(r'''(?x)<div[^>]+ | |
369bb062 | 170 | class=(?P<q1>[\'"])[^\'"]*\bfb-(?:video|post)\b[^\'"]*(?P=q1)[^>]+ |
6a424391 | 171 | data-href=(?P<q2>[\'"])(?P<url>(?:https?:)?//(?:www\.)?facebook.com/.+?)(?P=q2)''', webpage) |
fd6ca382 YCH |
172 | if mobj is not None: |
173 | return mobj.group('url') | |
174 | ||
67874aef JMF |
175 | def _login(self): |
176 | (useremail, password) = self._get_login_info() | |
9eae41dd PH |
177 | if useremail is None: |
178 | return | |
179 | ||
5c2266df | 180 | login_page_req = sanitized_Request(self._LOGIN_URL) |
c1f49e16 | 181 | self._set_cookie('facebook.com', 'locale', 'en_US') |
b74fa8cd | 182 | login_page = self._download_webpage(login_page_req, None, |
9e1a5b84 JW |
183 | note='Downloading login page', |
184 | errnote='Unable to download login page') | |
b37b9450 | 185 | lsd = self._search_regex( |
d0ff8384 | 186 | r'<input type="hidden" name="lsd" value="([^"]*)"', |
b37b9450 | 187 | login_page, 'lsd') |
cb3bb2cf | 188 | lgnrnd = self._search_regex(r'name="lgnrnd" value="([^"]*?)"', login_page, 'lgnrnd') |
67874aef | 189 | |
9eae41dd PH |
190 | login_form = { |
191 | 'email': useremail, | |
192 | 'pass': password, | |
67874aef JMF |
193 | 'lsd': lsd, |
194 | 'lgnrnd': lgnrnd, | |
195 | 'next': 'http://facebook.com/home.php', | |
196 | 'default_persistent': '0', | |
197 | 'legacy_return': '1', | |
198 | 'timezone': '-60', | |
199 | 'trynum': '1', | |
b74e86f4 | 200 | } |
5c2266df | 201 | request = sanitized_Request(self._LOGIN_URL, urlencode_postdata(login_form)) |
67874aef | 202 | request.add_header('Content-Type', 'application/x-www-form-urlencoded') |
9eae41dd | 203 | try: |
b74fa8cd | 204 | login_results = self._download_webpage(request, None, |
9e1a5b84 | 205 | note='Logging in', errnote='unable to fetch login page') |
9eae41dd | 206 | if re.search(r'<form(.*)name="login"(.*)</form>', login_results) is not None: |
9f66931e S |
207 | error = self._html_search_regex( |
208 | r'(?s)<div[^>]+class=(["\']).*?login_error_box.*?\1[^>]*><div[^>]*>.*?</div><div[^>]*>(?P<error>.+?)</div>', | |
209 | login_results, 'login error', default=None, group='error') | |
210 | if error: | |
211 | raise ExtractorError('Unable to login: %s' % error, expected=True) | |
dfb1b146 | 212 | self._downloader.report_warning('unable to log in: bad username/password, or exceeded login rate limit (~3/min). Check credentials or wait.') |
9eae41dd | 213 | return |
67874aef | 214 | |
c1f49e16 S |
215 | fb_dtsg = self._search_regex( |
216 | r'name="fb_dtsg" value="(.+?)"', login_results, 'fb_dtsg', default=None) | |
217 | h = self._search_regex( | |
218 | r'name="h"\s+(?:\w+="[^"]+"\s+)*?value="([^"]+)"', login_results, 'h', default=None) | |
219 | ||
220 | if not fb_dtsg or not h: | |
221 | return | |
222 | ||
67874aef | 223 | check_form = { |
c1f49e16 S |
224 | 'fb_dtsg': fb_dtsg, |
225 | 'h': h, | |
67874aef | 226 | 'name_action_selected': 'dont_save', |
67874aef | 227 | } |
5c2266df | 228 | check_req = sanitized_Request(self._CHECKPOINT_URL, urlencode_postdata(check_form)) |
67874aef | 229 | check_req.add_header('Content-Type', 'application/x-www-form-urlencoded') |
b74fa8cd | 230 | check_response = self._download_webpage(check_req, None, |
9e1a5b84 | 231 | note='Confirming login') |
67874aef | 232 | if re.search(r'id="checkpointSubmitButton"', check_response) is not None: |
dfb1b146 | 233 | self._downloader.report_warning('Unable to confirm login, you have to login in your browser and authorize the login.') |
9eae41dd | 234 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: |
9b9c5355 | 235 | self._downloader.report_warning('unable to log in: %s' % error_to_compat_str(err)) |
9eae41dd PH |
236 | return |
237 | ||
67874aef JMF |
238 | def _real_initialize(self): |
239 | self._login() | |
240 | ||
9c7b509b YCH |
241 | def _extract_from_url(self, url, video_id, fatal_if_no_video=True): |
242 | req = sanitized_Request(url) | |
0803753f YCH |
243 | req.add_header('User-Agent', self._CHROME_USER_AGENT) |
244 | webpage = self._download_webpage(req, video_id) | |
9eae41dd | 245 | |
c1406299 YCH |
246 | video_data = None |
247 | ||
b83ef507 S |
248 | def extract_video_data(instances): |
249 | for item in instances: | |
250 | if item[1][0] == 'VideoConfig': | |
251 | video_item = item[2][0] | |
252 | if video_item.get('video_id') == video_id: | |
253 | return video_item['videoData'] | |
254 | ||
d9ee2e5c | 255 | server_js_data = self._parse_json(self._search_regex( |
b83ef507 S |
256 | r'handleServerJS\(({.+})(?:\);|,")', webpage, |
257 | 'server js data', default='{}'), video_id, fatal=False) | |
258 | ||
259 | if server_js_data: | |
260 | video_data = extract_video_data(server_js_data.get('instances', [])) | |
261 | ||
262 | if not video_data: | |
263 | server_js_data = self._parse_json( | |
264 | self._search_regex( | |
265 | r'bigPipe\.onPageletArrive\(({.+?})\)\s*;\s*}\s*\)\s*,\s*["\']onPageletArrive\s+stream_pagelet', | |
266 | webpage, 'js data', default='{}'), | |
267 | video_id, transform_source=js_to_json, fatal=False) | |
268 | if server_js_data: | |
269 | video_data = extract_video_data(try_get( | |
270 | server_js_data, lambda x: x['jsmods']['instances'], | |
271 | list) or []) | |
c1406299 | 272 | |
c1406299 | 273 | if not video_data: |
9c7b509b YCH |
274 | if not fatal_if_no_video: |
275 | return webpage, False | |
6f71ef58 JMF |
276 | m_msg = re.search(r'class="[^"]*uiInterstitialContent[^"]*"><div>(.*?)</div>', webpage) |
277 | if m_msg is not None: | |
749a4fd2 | 278 | raise ExtractorError( |
cb3bb2cf | 279 | 'The video is not available, Facebook said: "%s"' % m_msg.group(1), |
749a4fd2 | 280 | expected=True) |
d2d2495e S |
281 | elif '>You must log in to continue' in webpage: |
282 | self.raise_login_required() | |
6f71ef58 | 283 | else: |
cb3bb2cf | 284 | raise ExtractorError('Cannot parse data') |
ffdf972b JMF |
285 | |
286 | formats = [] | |
d9ee2e5c YCH |
287 | for f in video_data: |
288 | format_id = f['stream_type'] | |
ca74c90b SC |
289 | if f and isinstance(f, dict): |
290 | f = [f] | |
44d6dd08 S |
291 | if not f or not isinstance(f, list): |
292 | continue | |
293 | for quality in ('sd', 'hd'): | |
294 | for src_type in ('src', 'src_no_ratelimit'): | |
295 | src = f[0].get('%s_%s' % (quality, src_type)) | |
296 | if src: | |
c24883a1 YCH |
297 | preference = -10 if format_id == 'progressive' else 0 |
298 | if quality == 'hd': | |
299 | preference += 5 | |
44d6dd08 S |
300 | formats.append({ |
301 | 'format_id': '%s_%s_%s' % (format_id, quality, src_type), | |
302 | 'url': src, | |
c24883a1 | 303 | 'preference': preference, |
44d6dd08 | 304 | }) |
0803753f YCH |
305 | dash_manifest = f[0].get('dash_manifest') |
306 | if dash_manifest: | |
91cb6b50 | 307 | formats.extend(self._parse_mpd_formats( |
c11875b3 | 308 | compat_etree_fromstring(compat_urllib_parse_unquote_plus(dash_manifest)))) |
ffdf972b JMF |
309 | if not formats: |
310 | raise ExtractorError('Cannot find video formats') | |
9eae41dd | 311 | |
0803753f YCH |
312 | self._sort_formats(formats) |
313 | ||
81ec7c79 | 314 | video_title = self._html_search_regex( |
bf24c3d0 | 315 | r'<h2\s+[^>]*class="uiHeaderTitle"[^>]*>([^<]*)</h2>', webpage, 'title', |
db3ca364 | 316 | default=None) |
50317dbb PH |
317 | if not video_title: |
318 | video_title = self._html_search_regex( | |
319 | r'(?s)<span class="fbPhotosPhotoCaption".*?id="fbPhotoPageCaption"><span class="hasCaption">(.*?)</span>', | |
59ee8a86 | 320 | webpage, 'alternative title', default=None) |
50317dbb | 321 | if not video_title: |
5a116e13 S |
322 | video_title = self._html_search_meta( |
323 | 'description', webpage, 'title') | |
324 | if video_title: | |
325 | video_title = limit_length(video_title, 80) | |
326 | else: | |
50317dbb | 327 | video_title = 'Facebook video #%s' % video_id |
5a116e13 S |
328 | uploader = clean_html(get_element_by_id( |
329 | 'fbPhotoPageAuthorName', webpage)) or self._search_regex( | |
330 | r'ownerName\s*:\s*"([^"]+)"', webpage, 'uploader', fatal=False) | |
196c6ba0 S |
331 | timestamp = int_or_none(self._search_regex( |
332 | r'<abbr[^>]+data-utime=["\'](\d+)', webpage, | |
333 | 'timestamp', default=None)) | |
9eae41dd | 334 | |
9c7b509b | 335 | info_dict = { |
9eae41dd PH |
336 | 'id': video_id, |
337 | 'title': video_title, | |
ffdf972b | 338 | 'formats': formats, |
51a57515 | 339 | 'uploader': uploader, |
196c6ba0 | 340 | 'timestamp': timestamp, |
9eae41dd | 341 | } |
de691a49 | 342 | |
9c7b509b | 343 | return webpage, info_dict |
de691a49 S |
344 | |
345 | def _real_extract(self, url): | |
9c7b509b YCH |
346 | video_id = self._match_id(url) |
347 | ||
348 | real_url = self._VIDEO_PAGE_TEMPLATE % video_id if url.startswith('facebook:') else url | |
349 | webpage, info_dict = self._extract_from_url(real_url, video_id, fatal_if_no_video=False) | |
de691a49 | 350 | |
9c7b509b YCH |
351 | if info_dict: |
352 | return info_dict | |
de691a49 | 353 | |
9c7b509b YCH |
354 | if '/posts/' in url: |
355 | entries = [ | |
f6f6217a JMF |
356 | self.url_result('facebook:%s' % vid, FacebookIE.ie_key()) |
357 | for vid in self._parse_json( | |
9c7b509b YCH |
358 | self._search_regex( |
359 | r'(["\'])video_ids\1\s*:\s*(?P<ids>\[.+?\])', | |
360 | webpage, 'video ids', group='ids'), | |
361 | video_id)] | |
de691a49 | 362 | |
9c7b509b YCH |
363 | return self.playlist_result(entries, video_id) |
364 | else: | |
365 | _, info_dict = self._extract_from_url( | |
366 | self._VIDEO_PAGE_TEMPLATE % video_id, | |
367 | video_id, fatal_if_no_video=True) | |
368 | return info_dict | |
349fc5c7 S |
369 | |
370 | ||
371 | class FacebookPluginsVideoIE(InfoExtractor): | |
372 | _VALID_URL = r'https?://(?:[\w-]+\.)?facebook\.com/plugins/video\.php\?.*?\bhref=(?P<id>https.+)' | |
373 | ||
374 | _TESTS = [{ | |
375 | 'url': 'https://www.facebook.com/plugins/video.php?href=https%3A%2F%2Fwww.facebook.com%2Fgov.sg%2Fvideos%2F10154383743583686%2F&show_text=0&width=560', | |
376 | 'md5': '5954e92cdfe51fe5782ae9bda7058a07', | |
377 | 'info_dict': { | |
378 | 'id': '10154383743583686', | |
379 | 'ext': 'mp4', | |
380 | 'title': 'What to do during the haze?', | |
381 | 'uploader': 'Gov.sg', | |
382 | 'upload_date': '20160826', | |
383 | 'timestamp': 1472184808, | |
384 | }, | |
385 | 'add_ie': [FacebookIE.ie_key()], | |
386 | }, { | |
387 | 'url': 'https://www.facebook.com/plugins/video.php?href=https%3A%2F%2Fwww.facebook.com%2Fvideo.php%3Fv%3D10204634152394104', | |
388 | 'only_matching': True, | |
389 | }, { | |
390 | 'url': 'https://www.facebook.com/plugins/video.php?href=https://www.facebook.com/gov.sg/videos/10154383743583686/&show_text=0&width=560', | |
391 | 'only_matching': True, | |
392 | }] | |
393 | ||
394 | def _real_extract(self, url): | |
395 | return self.url_result( | |
396 | compat_urllib_parse_unquote(self._match_id(url)), | |
397 | FacebookIE.ie_key()) |