From 9eae41ddefb3bbb4dc24ae4cfbc4f9fb20f0b859 Mon Sep 17 00:00:00 2001 From: Philipp Hagemeister Date: Sun, 23 Jun 2013 20:59:45 +0200 Subject: [PATCH] Move Facebook into its own file --- youtube_dl/InfoExtractors.py | 94 -------------------------- youtube_dl/extractor/facebook.py | 111 +++++++++++++++++++++++++++++++ 2 files changed, 111 insertions(+), 94 deletions(-) create mode 100644 youtube_dl/extractor/facebook.py diff --git a/youtube_dl/InfoExtractors.py b/youtube_dl/InfoExtractors.py index a1c1298df..9f2352ed9 100755 --- a/youtube_dl/InfoExtractors.py +++ b/youtube_dl/InfoExtractors.py @@ -101,100 +101,6 @@ class DepositFilesIE(InfoExtractor): }] -class FacebookIE(InfoExtractor): - """Information Extractor for Facebook""" - - _VALID_URL = r'^(?:https?://)?(?:\w+\.)?facebook\.com/(?:video/video|photo)\.php\?(?:.*?)v=(?P\d+)(?:.*)' - _LOGIN_URL = 'https://login.facebook.com/login.php?m&next=http%3A%2F%2Fm.facebook.com%2Fhome.php&' - _NETRC_MACHINE = 'facebook' - IE_NAME = u'facebook' - - def report_login(self): - """Report attempt to log in.""" - self.to_screen(u'Logging in') - - def _real_initialize(self): - if self._downloader is None: - return - - useremail = None - password = None - downloader_params = self._downloader.params - - # Attempt to use provided username and password or .netrc data - if downloader_params.get('username', None) is not None: - useremail = downloader_params['username'] - password = downloader_params['password'] - elif downloader_params.get('usenetrc', False): - try: - info = netrc.netrc().authenticators(self._NETRC_MACHINE) - if info is not None: - useremail = info[0] - password = info[2] - else: - raise netrc.NetrcParseError('No authenticators for %s' % self._NETRC_MACHINE) - except (IOError, netrc.NetrcParseError) as err: - self._downloader.report_warning(u'parsing .netrc: %s' % compat_str(err)) - return - - if useremail is None: - return - - # Log in - login_form = { - 'email': useremail, - 'pass': password, - 'login': 'Log+In' - } - request = compat_urllib_request.Request(self._LOGIN_URL, compat_urllib_parse.urlencode(login_form)) - try: - self.report_login() - 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 - except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: - self._downloader.report_warning(u'unable to log in: %s' % compat_str(err)) - return - - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - if mobj is None: - raise ExtractorError(u'Invalid URL: %s' % url) - video_id = mobj.group('ID') - - url = 'https://www.facebook.com/video/video.php?v=%s' % video_id - webpage = self._download_webpage(url, video_id) - - BEFORE = '{swf.addParam(param[0], param[1]);});\n' - AFTER = '.forEach(function(variable) {swf.addVariable(variable[0], variable[1]);});' - m = re.search(re.escape(BEFORE) + '(.*?)' + re.escape(AFTER), webpage) - if not m: - raise ExtractorError(u'Cannot parse data') - data = dict(json.loads(m.group(1))) - params_raw = compat_urllib_parse.unquote(data['params']) - params = json.loads(params_raw) - video_data = params['video_data'][0] - video_url = video_data.get('hd_src') - if not video_url: - video_url = video_data['sd_src'] - if not video_url: - raise ExtractorError(u'Cannot find video URL') - video_duration = int(video_data['video_duration']) - thumbnail = video_data['thumbnail_src'] - - video_title = self._html_search_regex('

([^<]+)

', - webpage, u'title') - - info = { - 'id': video_id, - 'title': video_title, - 'url': video_url, - 'ext': 'mp4', - 'duration': video_duration, - 'thumbnail': thumbnail, - } - return [info] diff --git a/youtube_dl/extractor/facebook.py b/youtube_dl/extractor/facebook.py new file mode 100644 index 000000000..c694f9adb --- /dev/null +++ b/youtube_dl/extractor/facebook.py @@ -0,0 +1,111 @@ +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://login.facebook.com/login.php?m&next=http%3A%2F%2Fm.facebook.com%2Fhome.php&' + _NETRC_MACHINE = 'facebook' + IE_NAME = u'facebook' + + def report_login(self): + """Report attempt to log in.""" + self.to_screen(u'Logging in') + + def _real_initialize(self): + if self._downloader is None: + return + + useremail = None + password = None + downloader_params = self._downloader.params + + # Attempt to use provided username and password or .netrc data + if downloader_params.get('username', None) is not None: + useremail = downloader_params['username'] + password = downloader_params['password'] + elif downloader_params.get('usenetrc', False): + try: + info = netrc.netrc().authenticators(self._NETRC_MACHINE) + if info is not None: + useremail = info[0] + password = info[2] + else: + raise netrc.NetrcParseError('No authenticators for %s' % self._NETRC_MACHINE) + except (IOError, netrc.NetrcParseError) as err: + self._downloader.report_warning(u'parsing .netrc: %s' % compat_str(err)) + return + + if useremail is None: + return + + # Log in + login_form = { + 'email': useremail, + 'pass': password, + 'login': 'Log+In' + } + request = compat_urllib_request.Request(self._LOGIN_URL, compat_urllib_parse.urlencode(login_form)) + try: + self.report_login() + 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 + except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: + self._downloader.report_warning(u'unable to log in: %s' % compat_str(err)) + return + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + if mobj is None: + raise ExtractorError(u'Invalid URL: %s' % url) + video_id = mobj.group('ID') + + url = 'https://www.facebook.com/video/video.php?v=%s' % video_id + webpage = self._download_webpage(url, video_id) + + BEFORE = '{swf.addParam(param[0], param[1]);});\n' + AFTER = '.forEach(function(variable) {swf.addVariable(variable[0], variable[1]);});' + m = re.search(re.escape(BEFORE) + '(.*?)' + re.escape(AFTER), webpage) + if not m: + raise ExtractorError(u'Cannot parse data') + data = dict(json.loads(m.group(1))) + params_raw = compat_urllib_parse.unquote(data['params']) + params = json.loads(params_raw) + video_data = params['video_data'][0] + video_url = video_data.get('hd_src') + if not video_url: + video_url = video_data['sd_src'] + if not video_url: + raise ExtractorError(u'Cannot find video URL') + video_duration = int(video_data['video_duration']) + thumbnail = video_data['thumbnail_src'] + + video_title = self._html_search_regex('

([^<]+)

', + webpage, u'title') + + info = { + 'id': video_id, + 'title': video_title, + 'url': video_url, + 'ext': 'mp4', + 'duration': video_duration, + 'thumbnail': thumbnail, + } + return [info]