From: Philipp Hagemeister Date: Sun, 25 Jan 2015 02:37:51 +0000 (+0100) Subject: Merge remote-tracking branch 'h-collector/master' X-Git-Url: http://git.oshgnacknak.de/?a=commitdiff_plain;h=8940b8608e567dba09b3ea146b89b297190ec6d6;p=youtube-dl Merge remote-tracking branch 'h-collector/master' Conflicts: youtube_dl/extractor/fc2.py --- 8940b8608e567dba09b3ea146b89b297190ec6d6 diff --cc youtube_dl/extractor/fc2.py index 81ceace53,3073ab0d4..1ccc1a964 --- a/youtube_dl/extractor/fc2.py +++ b/youtube_dl/extractor/fc2.py @@@ -4,7 -4,10 +4,8 @@@ from __future__ import unicode_literal import hashlib from .common import InfoExtractor -from ..utils import ( - ExtractorError, +from ..compat import ( + compat_urllib_parse, compat_urllib_request, compat_urlparse, ) @@@ -14,9 -14,10 +15,10 @@@ from ..utils import class FC2IE(InfoExtractor): - _VALID_URL = r'^http://video\.fc2\.com/((?P[^/]+)/)?(a/)?content/(?P[^/]+)' + _VALID_URL = r'^http://video\.fc2\.com/(?:[^/]+/)?content/(?P[^/]+)' IE_NAME = 'fc2' - _TEST = { + _NETRC_MACHINE = 'fc2' - _TEST = { ++ _TESTS = [{ 'url': 'http://video.fc2.com/en/content/20121103kUan1KHs', 'md5': 'a6ebe8ebe0396518689d963774a54eb7', 'info_dict': { @@@ -24,12 -25,50 +26,57 @@@ 'ext': 'flv', 'title': 'Boxing again with Puff', }, -- } - - #def _real_initialize(self): - # self._login() ++ }, { ++ 'url': 'http://video.fc2.com/en/content/20150125cEva0hDn/', ++ 'info_dict': { ++ 'id': '20150125cEva0hDn', ++ 'ext': 'mp4', ++ }, ++ 'params': { ++ 'username': 'ytdl@yt-dl.org', ++ 'password': '(snip)', ++ 'skip': 'requires actual password' ++ } ++ }] + + def _login(self): + (username, password) = self._get_login_info() - if (username is None) or (password is None): - self.to_screen('unable to log in: will be downloading in non authorized mode') # report_warning - return False ++ if username is None or password is None: ++ return False + + # Log in + login_form_strs = { - 'email': username, ++ 'email': username, + 'password': password, - 'done': 'video', - 'Submit': ' Login ', ++ 'done': 'video', ++ 'Submit': ' Login ', + } + + # Convert to UTF-8 *before* urlencode because Python 2.x's urlencode + # chokes on unicode + login_form = dict((k.encode('utf-8'), v.encode('utf-8')) for k, v in login_form_strs.items()) + login_data = compat_urllib_parse.urlencode(login_form).encode('utf-8') - request = compat_urllib_request.Request( ++ request = compat_urllib_request.Request( + 'https://secure.id.fc2.com/index.php?mode=login&switch_language=en', login_data) + + login_results = self._download_webpage(request, None, note='Logging in', errnote='Unable to log in') + if 'mode=redirect&login=done' not in login_results: - self.to_screen('unable to log in: bad username or password') # report_warning ++ self.report_warning('unable to log in: bad username or password') + return False - ++ + # this is also needed + login_redir = compat_urllib_request.Request('http://id.fc2.com/?mode=redirect&login=done') - redir_res = self._download_webpage(login_redir, None, note='Login redirect', errnote='Something is not right') ++ self._download_webpage( ++ login_redir, None, note='Login redirect', errnote='Login redirect failed') + + return True def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') - + video_id = self._match_id(url) ++ self._login() webpage = self._download_webpage(url, video_id) self._downloader.cookiejar.clear_session_cookies() # must clear + self._login() title = self._og_search_title(webpage) thumbnail = self._og_search_thumbnail(webpage) @@@ -46,7 -85,12 +93,12 @@@ info = compat_urlparse.parse_qs(info_webpage) if 'err_code' in info: - raise ExtractorError('Error code: %s' % info['err_code'][0]) - #raise ExtractorError('Error code: %s' % info['err_code'][0]) + # most of the time we can still download wideo even if err_code is 403 or 602 - self.to_screen('Error code was: %s... but still trying' % info['err_code'][0]) # report_warning ++ self.report_warning( ++ 'Error code was: %s... but still trying' % info['err_code'][0]) + + if 'filepath' not in info: - raise ExtractorError('Cannot download file. Are you logged?') ++ raise ExtractorError('Cannot download file. Are you logged in?') video_url = info['filepath'][0] + '?mid=' + info['mid'][0] title_info = info.get('title')