]>
Commit | Line | Data |
---|---|---|
9eae41dd | 1 | import json |
9eae41dd PH |
2 | import re |
3 | import socket | |
4 | ||
5 | from .common import InfoExtractor | |
6 | from ..utils import ( | |
7 | compat_http_client, | |
8 | compat_str, | |
9 | compat_urllib_error, | |
10 | compat_urllib_parse, | |
11 | compat_urllib_request, | |
12 | ||
13 | ExtractorError, | |
14 | ) | |
15 | ||
16 | ||
17 | class FacebookIE(InfoExtractor): | |
18 | """Information Extractor for Facebook""" | |
19 | ||
8c8e3eec | 20 | _VALID_URL = r'^(?:https?://)?(?:\w+\.)?facebook\.com/(?:[^#?]*#!/)?(?:video/video|photo)\.php\?(?:.*?)v=(?P<ID>\d+)(?:.*)' |
67874aef JMF |
21 | _LOGIN_URL = 'https://www.facebook.com/login.php?next=http%3A%2F%2Ffacebook.com%2Fhome.php&login_attempt=1' |
22 | _CHECKPOINT_URL = 'https://www.facebook.com/checkpoint/?next=http%3A%2F%2Ffacebook.com%2Fhome.php&_fb_noscript=1' | |
9eae41dd PH |
23 | _NETRC_MACHINE = 'facebook' |
24 | IE_NAME = u'facebook' | |
6f5ac90c PH |
25 | _TEST = { |
26 | u'url': u'https://www.facebook.com/photo.php?v=120708114770723', | |
27 | u'file': u'120708114770723.mp4', | |
28 | u'md5': u'48975a41ccc4b7a581abd68651c1a5a8', | |
29 | u'info_dict': { | |
8c8e3eec | 30 | u"duration": 279, |
6f5ac90c PH |
31 | u"title": u"PEOPLE ARE AWESOME 2013" |
32 | } | |
33 | } | |
9eae41dd PH |
34 | |
35 | def report_login(self): | |
36 | """Report attempt to log in.""" | |
37 | self.to_screen(u'Logging in') | |
38 | ||
67874aef JMF |
39 | def _login(self): |
40 | (useremail, password) = self._get_login_info() | |
9eae41dd PH |
41 | if useremail is None: |
42 | return | |
43 | ||
67874aef JMF |
44 | login_page_req = compat_urllib_request.Request(self._LOGIN_URL) |
45 | login_page_req.add_header('Cookie', 'locale=en_US') | |
46 | self.report_login() | |
47 | login_page = self._download_webpage(login_page_req, None, note=False, | |
48 | errnote=u'Unable to download login page') | |
49 | lsd = self._search_regex(r'"lsd":"(\w*?)"', login_page, u'lsd') | |
50 | lgnrnd = self._search_regex(r'name="lgnrnd" value="([^"]*?)"', login_page, u'lgnrnd') | |
51 | ||
9eae41dd PH |
52 | login_form = { |
53 | 'email': useremail, | |
54 | 'pass': password, | |
67874aef JMF |
55 | 'lsd': lsd, |
56 | 'lgnrnd': lgnrnd, | |
57 | 'next': 'http://facebook.com/home.php', | |
58 | 'default_persistent': '0', | |
59 | 'legacy_return': '1', | |
60 | 'timezone': '-60', | |
61 | 'trynum': '1', | |
9eae41dd PH |
62 | } |
63 | request = compat_urllib_request.Request(self._LOGIN_URL, compat_urllib_parse.urlencode(login_form)) | |
67874aef | 64 | request.add_header('Content-Type', 'application/x-www-form-urlencoded') |
9eae41dd | 65 | try: |
9eae41dd PH |
66 | login_results = compat_urllib_request.urlopen(request).read() |
67 | if re.search(r'<form(.*)name="login"(.*)</form>', login_results) is not None: | |
68 | self._downloader.report_warning(u'unable to log in: bad username/password, or exceded login rate limit (~3/min). Check credentials or wait.') | |
69 | return | |
67874aef JMF |
70 | |
71 | check_form = { | |
72 | 'fb_dtsg': self._search_regex(r'"fb_dtsg":"(.*?)"', login_results, u'fb_dtsg'), | |
73 | 'nh': self._search_regex(r'name="nh" value="(\w*?)"', login_results, u'nh'), | |
74 | 'name_action_selected': 'dont_save', | |
75 | 'submit[Continue]': self._search_regex(r'<input value="(.*?)" name="submit\[Continue\]"', login_results, u'continue'), | |
76 | } | |
77 | check_req = compat_urllib_request.Request(self._CHECKPOINT_URL, compat_urllib_parse.urlencode(check_form)) | |
78 | check_req.add_header('Content-Type', 'application/x-www-form-urlencoded') | |
79 | check_response = compat_urllib_request.urlopen(check_req).read() | |
80 | if re.search(r'id="checkpointSubmitButton"', check_response) is not None: | |
81 | self._downloader.report_warning(u'Unable to confirm login, you have to login in your brower and authorize the login.') | |
9eae41dd PH |
82 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: |
83 | self._downloader.report_warning(u'unable to log in: %s' % compat_str(err)) | |
84 | return | |
85 | ||
67874aef JMF |
86 | def _real_initialize(self): |
87 | self._login() | |
88 | ||
9eae41dd PH |
89 | def _real_extract(self, url): |
90 | mobj = re.match(self._VALID_URL, url) | |
91 | if mobj is None: | |
92 | raise ExtractorError(u'Invalid URL: %s' % url) | |
93 | video_id = mobj.group('ID') | |
94 | ||
95 | url = 'https://www.facebook.com/video/video.php?v=%s' % video_id | |
96 | webpage = self._download_webpage(url, video_id) | |
97 | ||
98 | BEFORE = '{swf.addParam(param[0], param[1]);});\n' | |
99 | AFTER = '.forEach(function(variable) {swf.addVariable(variable[0], variable[1]);});' | |
100 | m = re.search(re.escape(BEFORE) + '(.*?)' + re.escape(AFTER), webpage) | |
101 | if not m: | |
6f71ef58 JMF |
102 | m_msg = re.search(r'class="[^"]*uiInterstitialContent[^"]*"><div>(.*?)</div>', webpage) |
103 | if m_msg is not None: | |
749a4fd2 JMF |
104 | raise ExtractorError( |
105 | u'The video is not available, Facebook said: "%s"' % m_msg.group(1), | |
106 | expected=True) | |
6f71ef58 | 107 | else: |
749a4fd2 | 108 | raise ExtractorError(u'Cannot parse data') |
9eae41dd PH |
109 | data = dict(json.loads(m.group(1))) |
110 | params_raw = compat_urllib_parse.unquote(data['params']) | |
111 | params = json.loads(params_raw) | |
112 | video_data = params['video_data'][0] | |
113 | video_url = video_data.get('hd_src') | |
114 | if not video_url: | |
115 | video_url = video_data['sd_src'] | |
116 | if not video_url: | |
117 | raise ExtractorError(u'Cannot find video URL') | |
118 | video_duration = int(video_data['video_duration']) | |
119 | thumbnail = video_data['thumbnail_src'] | |
120 | ||
81ec7c79 PH |
121 | video_title = self._html_search_regex( |
122 | r'<h2 class="uiHeaderTitle">([^<]*)</h2>', webpage, u'title') | |
9eae41dd PH |
123 | |
124 | info = { | |
125 | 'id': video_id, | |
126 | 'title': video_title, | |
127 | 'url': video_url, | |
128 | 'ext': 'mp4', | |
129 | 'duration': video_duration, | |
130 | 'thumbnail': thumbnail, | |
131 | } | |
132 | return [info] |