From 7f7801e77687da91d3376c4642d7f98b43a6909c Mon Sep 17 00:00:00 2001 From: carsten demming Date: Tue, 20 Feb 2018 12:00:25 +0100 Subject: [PATCH 1/5] - added vol.at extractor template --- youtube_dl/extractor/extractors.py | 3 ++- youtube_dl/extractor/volat.py | 40 ++++++++++++++++++++++++++++++ 2 files changed, 42 insertions(+), 1 deletion(-) create mode 100644 youtube_dl/extractor/volat.py diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index b2a4893fe..6f42d66da 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -1269,6 +1269,7 @@ from .vodlocker import VodlockerIE from .vodpl import VODPlIE from .vodplatform import VODPlatformIE from .voicerepublic import VoiceRepublicIE +from .volat import VolAtIE from .voot import VootIE from .voxmedia import ( VoxMediaVolumeIE, @@ -1311,7 +1312,7 @@ from .webofstories import ( WebOfStoriesPlaylistIE, ) from .weibo import ( - WeiboIE, + WeiboIE, WeiboMobileIE ) from .weiqitv import WeiqiTVIE diff --git a/youtube_dl/extractor/volat.py b/youtube_dl/extractor/volat.py new file mode 100644 index 000000000..8afe6616c --- /dev/null +++ b/youtube_dl/extractor/volat.py @@ -0,0 +1,40 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor + + +class VolAtIE(InfoExtractor): + print("wtf") + _VALID_URL = r'https?://(?:www\.)?vol\.at/(?P[0-9]+)' + _TEST = { + 'url': 'http://www.vol.at/blue-man-group/5593454', + 'md5': 'TODO: md5 sum of the first 10241 bytes of the video file (use --test)', + 'info_dict': { + 'id': '5593454', + 'ext': 'mp4', + 'title': '"Blau ist mysteriös": Die Blue Man Group im Interview', + 'thumbnail': r're:^https?://.*\.jpg$', + # TODO more properties, either as: + # * A value + # * MD5 checksum; start the string with md5: + # * A regular expression; start the string with re: + # * Any Python type (for example int or float) + } + } + + def _real_extract(self, url): + print("hello test") + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) + + # TODO more code goes here, for example ... + title = self._html_search_regex(r'

(.+?)

', webpage, 'title') + + return { + 'id': video_id, + 'title': title, + 'description': self._og_search_description(webpage), + 'uploader': self._search_regex(r']+id="uploader"[^>]*>([^<]+)<', webpage, 'uploader', fatal=False), + # TODO more properties (see youtube_dl/extractor/common.py) + } From b3a3b9ab6ca22c47be9a708c67b97b4c9509dded Mon Sep 17 00:00:00 2001 From: carsten demming Date: Tue, 20 Feb 2018 12:01:15 +0100 Subject: [PATCH 2/5] - fixed xhamster test category array --- youtube_dl/extractor/xhamster.py | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/xhamster.py b/youtube_dl/extractor/xhamster.py index 68652a22f..90b722f68 100644 --- a/youtube_dl/extractor/xhamster.py +++ b/youtube_dl/extractor/xhamster.py @@ -39,7 +39,7 @@ class XHamsterIE(InfoExtractor): 'uploader': 'Ruseful2011', 'duration': 893, 'age_limit': 18, - 'categories': ['Fake Hub', 'Amateur', 'MILFs', 'POV', 'Boss', 'Office', 'Oral', 'Reality', 'Sexy'], + 'categories': ['Fake Hub', 'Amateur', 'MILFs', 'POV', 'Beauti', 'Beauties', 'Beautiful', 'Boss', 'Office', 'Oral', 'Reality', 'Sexy', 'Taking'], }, }, { 'url': 'http://xhamster.com/movies/2221348/britney_spears_sexy_booty.html?hd', @@ -93,6 +93,7 @@ class XHamsterIE(InfoExtractor): }] def _real_extract(self, url): + #print("COME ON WTF") mobj = re.match(self._VALID_URL, url) video_id = mobj.group('id') or mobj.group('id_2') display_id = mobj.group('display_id') or mobj.group('display_id_2') From 0d1adaef3980a8c921b1f164254048a17395d092 Mon Sep 17 00:00:00 2001 From: carsten demming Date: Tue, 20 Feb 2018 12:07:31 +0100 Subject: [PATCH 3/5] - removed print --- youtube_dl/extractor/xhamster.py | 1 - 1 file changed, 1 deletion(-) diff --git a/youtube_dl/extractor/xhamster.py b/youtube_dl/extractor/xhamster.py index 90b722f68..d1bc992fd 100644 --- a/youtube_dl/extractor/xhamster.py +++ b/youtube_dl/extractor/xhamster.py @@ -93,7 +93,6 @@ class XHamsterIE(InfoExtractor): }] def _real_extract(self, url): - #print("COME ON WTF") mobj = re.match(self._VALID_URL, url) video_id = mobj.group('id') or mobj.group('id_2') display_id = mobj.group('display_id') or mobj.group('display_id_2') From 84c9501d6f92fb618f53a1080df0e47873f2f244 Mon Sep 17 00:00:00 2001 From: carsten demming Date: Tue, 20 Feb 2018 12:19:41 +0100 Subject: [PATCH 4/5] - removed wrong commits(different branch) --- youtube_dl/extractor/extractors.py | 1 - youtube_dl/extractor/volat.py | 40 ------------------------------ 2 files changed, 41 deletions(-) delete mode 100644 youtube_dl/extractor/volat.py diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 6f42d66da..def4eee14 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -1269,7 +1269,6 @@ from .vodlocker import VodlockerIE from .vodpl import VODPlIE from .vodplatform import VODPlatformIE from .voicerepublic import VoiceRepublicIE -from .volat import VolAtIE from .voot import VootIE from .voxmedia import ( VoxMediaVolumeIE, diff --git a/youtube_dl/extractor/volat.py b/youtube_dl/extractor/volat.py deleted file mode 100644 index 8afe6616c..000000000 --- a/youtube_dl/extractor/volat.py +++ /dev/null @@ -1,40 +0,0 @@ -# coding: utf-8 -from __future__ import unicode_literals - -from .common import InfoExtractor - - -class VolAtIE(InfoExtractor): - print("wtf") - _VALID_URL = r'https?://(?:www\.)?vol\.at/(?P[0-9]+)' - _TEST = { - 'url': 'http://www.vol.at/blue-man-group/5593454', - 'md5': 'TODO: md5 sum of the first 10241 bytes of the video file (use --test)', - 'info_dict': { - 'id': '5593454', - 'ext': 'mp4', - 'title': '"Blau ist mysteriös": Die Blue Man Group im Interview', - 'thumbnail': r're:^https?://.*\.jpg$', - # TODO more properties, either as: - # * A value - # * MD5 checksum; start the string with md5: - # * A regular expression; start the string with re: - # * Any Python type (for example int or float) - } - } - - def _real_extract(self, url): - print("hello test") - video_id = self._match_id(url) - webpage = self._download_webpage(url, video_id) - - # TODO more code goes here, for example ... - title = self._html_search_regex(r'

(.+?)

', webpage, 'title') - - return { - 'id': video_id, - 'title': title, - 'description': self._og_search_description(webpage), - 'uploader': self._search_regex(r']+id="uploader"[^>]*>([^<]+)<', webpage, 'uploader', fatal=False), - # TODO more properties (see youtube_dl/extractor/common.py) - } From 26aae0fa3ea292ca80b68ff9d9bdbd010b8a64fd Mon Sep 17 00:00:00 2001 From: carsten demming Date: Tue, 20 Feb 2018 12:21:14 +0100 Subject: [PATCH 5/5] - removed weibo autochange --- youtube_dl/extractor/extractors.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index def4eee14..b2a4893fe 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -1311,7 +1311,7 @@ from .webofstories import ( WebOfStoriesPlaylistIE, ) from .weibo import ( - WeiboIE, + WeiboIE, WeiboMobileIE ) from .weiqitv import WeiqiTVIE