import json import netrc import re import socket from .common import InfoExtractor from ..utils import ( compat_http_client, compat_str, compat_urllib_error, compat_urllib_parse, compat_urllib_request, ExtractorError, ) class FacebookIE(InfoExtractor): """Information Extractor for Facebook""" _VALID_URL = r'^(?:https?://)?(?:\w+\.)?facebook\.com/(?:video/video|photo)\.php\?(?:.*?)v=(?P\d+)(?:.*)' _LOGIN_URL = 'https://www.facebook.com/login.php?next=http%3A%2F%2Ffacebook.com%2Fhome.php&login_attempt=1' _CHECKPOINT_URL = 'https://www.facebook.com/checkpoint/?next=http%3A%2F%2Ffacebook.com%2Fhome.php&_fb_noscript=1' _NETRC_MACHINE = 'facebook' IE_NAME = u'facebook' _TEST = { u'url': u'https://www.facebook.com/photo.php?v=120708114770723', u'file': u'120708114770723.mp4', u'md5': u'48975a41ccc4b7a581abd68651c1a5a8', u'info_dict': { u"duration": 279, u"title": u"PEOPLE ARE AWESOME 2013" } } def report_login(self): """Report attempt to log in.""" self.to_screen(u'Logging in') def _login(self): (useremail, password) = self._get_login_info() if useremail is None: return login_page_req = compat_urllib_request.Request(self._LOGIN_URL) login_page_req.add_header('Cookie', 'locale=en_US') self.report_login() login_page = self._download_webpage(login_page_req, None, note=False, errnote=u'Unable to download login page') lsd = self._search_regex(r'"lsd":"(\w*?)"', login_page, u'lsd') lgnrnd = self._search_regex(r'name="lgnrnd" value="([^"]*?)"', login_page, u'lgnrnd') login_form = { 'email': useremail, 'pass': password, 'lsd': lsd, 'lgnrnd': lgnrnd, 'next': 'http://facebook.com/home.php', 'default_persistent': '0', 'legacy_return': '1', 'timezone': '-60', 'trynum': '1', } request = compat_urllib_request.Request(self._LOGIN_URL, compat_urllib_parse.urlencode(login_form)) request.add_header('Content-Type', 'application/x-www-form-urlencoded') try: login_results = compat_urllib_request.urlopen(request).read() if re.search(r'', login_results) is not None: self._downloader.report_warning(u'unable to log in: bad username/password, or exceded login rate limit (~3/min). Check credentials or wait.') return check_form = { 'fb_dtsg': self._search_regex(r'"fb_dtsg":"(.*?)"', login_results, u'fb_dtsg'), 'nh': self._search_regex(r'name="nh" value="(\w*?)"', login_results, u'nh'), 'name_action_selected': 'dont_save', 'submit[Continue]': self._search_regex(r'([^<]*)', webpage, u'title') info = { 'id': video_id, 'title': video_title, 'url': video_url, 'ext': 'mp4', 'duration': video_duration, 'thumbnail': thumbnail, } return [info]