]>
Commit | Line | Data |
---|---|---|
cb3bb2cf PH |
1 | from __future__ import unicode_literals |
2 | ||
9eae41dd | 3 | import json |
9eae41dd PH |
4 | import re |
5 | import socket | |
6 | ||
7 | from .common import InfoExtractor | |
8c25f81b | 8 | from ..compat import ( |
9eae41dd | 9 | compat_http_client, |
9eae41dd | 10 | compat_urllib_error, |
d7011316 | 11 | compat_urllib_parse_unquote, |
8c25f81b PH |
12 | ) |
13 | from ..utils import ( | |
9b9c5355 | 14 | error_to_compat_str, |
9eae41dd | 15 | ExtractorError, |
a020a0dc | 16 | limit_length, |
5c2266df | 17 | sanitized_Request, |
2fc9f2b4 | 18 | urlencode_postdata, |
51a57515 | 19 | get_element_by_id, |
20 | clean_html, | |
9eae41dd PH |
21 | ) |
22 | ||
23 | ||
24 | class FacebookIE(InfoExtractor): | |
9834872b | 25 | _VALID_URL = r'''(?x) |
9d9d70c4 | 26 | https?://(?:\w+\.)?facebook\.com/ |
a6da7b6b | 27 | (?:[^#]*?\#!/)? |
c6256697 YCH |
28 | (?: |
29 | (?:video/video\.php|photo\.php|video\.php|video/embed)\?(?:.*?) | |
30 | (?:v|video_id)=| | |
53faa3ca | 31 | [^/]+/videos/(?:[^/]+/)? |
c6256697 YCH |
32 | ) |
33 | (?P<id>[0-9]+) | |
9834872b | 34 | (?:.*)''' |
67874aef JMF |
35 | _LOGIN_URL = 'https://www.facebook.com/login.php?next=http%3A%2F%2Ffacebook.com%2Fhome.php&login_attempt=1' |
36 | _CHECKPOINT_URL = 'https://www.facebook.com/checkpoint/?next=http%3A%2F%2Ffacebook.com%2Fhome.php&_fb_noscript=1' | |
9eae41dd | 37 | _NETRC_MACHINE = 'facebook' |
cb3bb2cf | 38 | IE_NAME = 'facebook' |
60ac04e5 | 39 | _TESTS = [{ |
50317dbb PH |
40 | 'url': 'https://www.facebook.com/video.php?v=637842556329505&fref=nf', |
41 | 'md5': '6a40d33c0eccbb1af76cf0485a052659', | |
cb3bb2cf | 42 | 'info_dict': { |
50317dbb | 43 | 'id': '637842556329505', |
cb3bb2cf | 44 | 'ext': 'mp4', |
5e4f0619 | 45 | 'title': 're:Did you know Kei Nishikori is the first Asian man to ever reach a Grand Slam', |
67b8a28a | 46 | 'uploader': 'Tennis on Facebook', |
6f5ac90c | 47 | } |
a020a0dc PH |
48 | }, { |
49 | 'note': 'Video without discernible title', | |
50 | 'url': 'https://www.facebook.com/video.php?v=274175099429670', | |
51 | 'info_dict': { | |
52 | 'id': '274175099429670', | |
53 | 'ext': 'mp4', | |
54 | 'title': 'Facebook video #274175099429670', | |
67b8a28a | 55 | 'uploader': 'Asif Nawab Butt', |
db3ca364 YCH |
56 | }, |
57 | 'expected_warnings': [ | |
58 | 'title' | |
59 | ] | |
60ac04e5 PH |
60 | }, { |
61 | 'url': 'https://www.facebook.com/video.php?v=10204634152394104', | |
62 | 'only_matching': True, | |
c6256697 YCH |
63 | }, { |
64 | 'url': 'https://www.facebook.com/amogood/videos/1618742068337349/?fref=nf', | |
65 | 'only_matching': True, | |
53faa3ca YCH |
66 | }, { |
67 | 'url': 'https://www.facebook.com/ChristyClarkForBC/videos/vb.22819070941/10153870694020942/?type=2&theater', | |
68 | 'only_matching': True, | |
60ac04e5 | 69 | }] |
9eae41dd | 70 | |
67874aef JMF |
71 | def _login(self): |
72 | (useremail, password) = self._get_login_info() | |
9eae41dd PH |
73 | if useremail is None: |
74 | return | |
75 | ||
5c2266df | 76 | login_page_req = sanitized_Request(self._LOGIN_URL) |
c1f49e16 | 77 | self._set_cookie('facebook.com', 'locale', 'en_US') |
b74fa8cd | 78 | login_page = self._download_webpage(login_page_req, None, |
9e1a5b84 JW |
79 | note='Downloading login page', |
80 | errnote='Unable to download login page') | |
b37b9450 | 81 | lsd = self._search_regex( |
d0ff8384 | 82 | r'<input type="hidden" name="lsd" value="([^"]*)"', |
b37b9450 | 83 | login_page, 'lsd') |
cb3bb2cf | 84 | lgnrnd = self._search_regex(r'name="lgnrnd" value="([^"]*?)"', login_page, 'lgnrnd') |
67874aef | 85 | |
9eae41dd PH |
86 | login_form = { |
87 | 'email': useremail, | |
88 | 'pass': password, | |
67874aef JMF |
89 | 'lsd': lsd, |
90 | 'lgnrnd': lgnrnd, | |
91 | 'next': 'http://facebook.com/home.php', | |
92 | 'default_persistent': '0', | |
93 | 'legacy_return': '1', | |
94 | 'timezone': '-60', | |
95 | 'trynum': '1', | |
b74e86f4 | 96 | } |
5c2266df | 97 | request = sanitized_Request(self._LOGIN_URL, urlencode_postdata(login_form)) |
67874aef | 98 | request.add_header('Content-Type', 'application/x-www-form-urlencoded') |
9eae41dd | 99 | try: |
b74fa8cd | 100 | login_results = self._download_webpage(request, None, |
9e1a5b84 | 101 | note='Logging in', errnote='unable to fetch login page') |
9eae41dd | 102 | if re.search(r'<form(.*)name="login"(.*)</form>', login_results) is not None: |
9f66931e S |
103 | error = self._html_search_regex( |
104 | r'(?s)<div[^>]+class=(["\']).*?login_error_box.*?\1[^>]*><div[^>]*>.*?</div><div[^>]*>(?P<error>.+?)</div>', | |
105 | login_results, 'login error', default=None, group='error') | |
106 | if error: | |
107 | raise ExtractorError('Unable to login: %s' % error, expected=True) | |
cb3bb2cf | 108 | self._downloader.report_warning('unable to log in: bad username/password, or exceded login rate limit (~3/min). Check credentials or wait.') |
9eae41dd | 109 | return |
67874aef | 110 | |
c1f49e16 S |
111 | fb_dtsg = self._search_regex( |
112 | r'name="fb_dtsg" value="(.+?)"', login_results, 'fb_dtsg', default=None) | |
113 | h = self._search_regex( | |
114 | r'name="h"\s+(?:\w+="[^"]+"\s+)*?value="([^"]+)"', login_results, 'h', default=None) | |
115 | ||
116 | if not fb_dtsg or not h: | |
117 | return | |
118 | ||
67874aef | 119 | check_form = { |
c1f49e16 S |
120 | 'fb_dtsg': fb_dtsg, |
121 | 'h': h, | |
67874aef | 122 | 'name_action_selected': 'dont_save', |
67874aef | 123 | } |
5c2266df | 124 | check_req = sanitized_Request(self._CHECKPOINT_URL, urlencode_postdata(check_form)) |
67874aef | 125 | check_req.add_header('Content-Type', 'application/x-www-form-urlencoded') |
b74fa8cd | 126 | check_response = self._download_webpage(check_req, None, |
9e1a5b84 | 127 | note='Confirming login') |
67874aef | 128 | if re.search(r'id="checkpointSubmitButton"', check_response) is not None: |
cb3bb2cf | 129 | self._downloader.report_warning('Unable to confirm login, you have to login in your brower and authorize the login.') |
9eae41dd | 130 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: |
9b9c5355 | 131 | self._downloader.report_warning('unable to log in: %s' % error_to_compat_str(err)) |
9eae41dd PH |
132 | return |
133 | ||
67874aef JMF |
134 | def _real_initialize(self): |
135 | self._login() | |
136 | ||
9eae41dd | 137 | def _real_extract(self, url): |
2fc9f2b4 | 138 | video_id = self._match_id(url) |
9eae41dd PH |
139 | url = 'https://www.facebook.com/video/video.php?v=%s' % video_id |
140 | webpage = self._download_webpage(url, video_id) | |
141 | ||
142 | BEFORE = '{swf.addParam(param[0], param[1]);});\n' | |
143 | AFTER = '.forEach(function(variable) {swf.addVariable(variable[0], variable[1]);});' | |
144 | m = re.search(re.escape(BEFORE) + '(.*?)' + re.escape(AFTER), webpage) | |
145 | if not m: | |
6f71ef58 JMF |
146 | m_msg = re.search(r'class="[^"]*uiInterstitialContent[^"]*"><div>(.*?)</div>', webpage) |
147 | if m_msg is not None: | |
749a4fd2 | 148 | raise ExtractorError( |
cb3bb2cf | 149 | 'The video is not available, Facebook said: "%s"' % m_msg.group(1), |
749a4fd2 | 150 | expected=True) |
6f71ef58 | 151 | else: |
cb3bb2cf | 152 | raise ExtractorError('Cannot parse data') |
9eae41dd | 153 | data = dict(json.loads(m.group(1))) |
d7011316 | 154 | params_raw = compat_urllib_parse_unquote(data['params']) |
9eae41dd | 155 | params = json.loads(params_raw) |
ffdf972b JMF |
156 | |
157 | formats = [] | |
44d6dd08 S |
158 | for format_id, f in params['video_data'].items(): |
159 | if not f or not isinstance(f, list): | |
160 | continue | |
161 | for quality in ('sd', 'hd'): | |
162 | for src_type in ('src', 'src_no_ratelimit'): | |
163 | src = f[0].get('%s_%s' % (quality, src_type)) | |
164 | if src: | |
165 | formats.append({ | |
166 | 'format_id': '%s_%s_%s' % (format_id, quality, src_type), | |
167 | 'url': src, | |
168 | 'preference': -10 if format_id == 'progressive' else 0, | |
169 | }) | |
ffdf972b JMF |
170 | if not formats: |
171 | raise ExtractorError('Cannot find video formats') | |
9eae41dd | 172 | |
81ec7c79 | 173 | video_title = self._html_search_regex( |
bf24c3d0 | 174 | r'<h2\s+[^>]*class="uiHeaderTitle"[^>]*>([^<]*)</h2>', webpage, 'title', |
db3ca364 | 175 | default=None) |
50317dbb PH |
176 | if not video_title: |
177 | video_title = self._html_search_regex( | |
178 | r'(?s)<span class="fbPhotosPhotoCaption".*?id="fbPhotoPageCaption"><span class="hasCaption">(.*?)</span>', | |
59ee8a86 | 179 | webpage, 'alternative title', default=None) |
a020a0dc | 180 | video_title = limit_length(video_title, 80) |
50317dbb PH |
181 | if not video_title: |
182 | video_title = 'Facebook video #%s' % video_id | |
51a57515 | 183 | uploader = clean_html(get_element_by_id('fbPhotoPageAuthorName', webpage)) |
9eae41dd | 184 | |
9d9d70c4 | 185 | return { |
9eae41dd PH |
186 | 'id': video_id, |
187 | 'title': video_title, | |
ffdf972b | 188 | 'formats': formats, |
51a57515 | 189 | 'uploader': uploader, |
9eae41dd | 190 | } |