diff options
Diffstat (limited to 'youtube_dl')
-rw-r--r-- | youtube_dl/extractor/__init__.py | 1 | ||||
-rw-r--r-- | youtube_dl/extractor/fivemin.py | 13 | ||||
-rw-r--r-- | youtube_dl/extractor/rtbf.py | 49 | ||||
-rw-r--r-- | youtube_dl/extractor/scivee.py | 8 | ||||
-rw-r--r-- | youtube_dl/extractor/syfy.py | 28 | ||||
-rw-r--r-- | youtube_dl/extractor/theplatform.py | 2 |
6 files changed, 92 insertions, 9 deletions
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 410187963..e27cd2d2d 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -211,6 +211,7 @@ from .ringtv import RingTVIE from .ro220 import Ro220IE from .rottentomatoes import RottenTomatoesIE from .roxwel import RoxwelIE +from .rtbf import RTBFIE from .rtlnow import RTLnowIE from .rts import RTSIE from .rtve import RTVEALaCartaIE diff --git a/youtube_dl/extractor/fivemin.py b/youtube_dl/extractor/fivemin.py index b596bf587..3a50bab5c 100644 --- a/youtube_dl/extractor/fivemin.py +++ b/youtube_dl/extractor/fivemin.py @@ -6,6 +6,7 @@ from .common import InfoExtractor from ..utils import ( compat_str, compat_urllib_parse, + ExtractorError, ) @@ -58,9 +59,17 @@ class FiveMinIE(InfoExtractor): 'isPlayerSeed': 'true', 'url': embed_url, }) - info = self._download_json( + response = self._download_json( 'https://syn.5min.com/handlers/SenseHandler.ashx?' + query, - video_id)['binding'][0] + video_id) + if not response['success']: + err_msg = response['errorMessage'] + if err_msg == 'ErrorVideoUserNotGeo': + msg = 'Video not available from your location' + else: + msg = 'Aol said: %s' % err_msg + raise ExtractorError(msg, expected=True, video_id=video_id) + info = response['binding'][0] second_id = compat_str(int(video_id[:-2]) + 1) formats = [] diff --git a/youtube_dl/extractor/rtbf.py b/youtube_dl/extractor/rtbf.py new file mode 100644 index 000000000..205f8a167 --- /dev/null +++ b/youtube_dl/extractor/rtbf.py @@ -0,0 +1,49 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re +import json + +from .common import InfoExtractor + + +class RTBFIE(InfoExtractor): + _VALID_URL = r'https?://www.rtbf.be/video/[^\?]+\?id=(?P<id>\d+)' + _TEST = { + 'url': 'https://www.rtbf.be/video/detail_les-diables-au-coeur-episode-2?id=1921274', + 'md5': '799f334ddf2c0a582ba80c44655be570', + 'info_dict': { + 'id': '1921274', + 'ext': 'mp4', + 'title': 'Les Diables au coeur (épisode 2)', + 'description': 'Football - Diables Rouges', + 'duration': 3099, + 'timestamp': 1398456336, + 'upload_date': '20140425', + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + page = self._download_webpage('https://www.rtbf.be/video/embed?id=%s' % video_id, video_id) + + data = json.loads(self._html_search_regex( + r'<div class="js-player-embed" data-video="([^"]+)"', page, 'data video'))['data'] + + video_url = data.get('downloadUrl') or data.get('url') + + if data['provider'].lower() == 'youtube': + return self.url_result(video_url, 'Youtube') + + return { + 'id': video_id, + 'url': video_url, + 'title': data['title'], + 'description': data.get('description') or data.get('subtitle'), + 'thumbnail': data['thumbnail']['large'], + 'duration': data.get('duration') or data.get('realDuration'), + 'timestamp': data['created'], + 'view_count': data['viewCount'], + } diff --git a/youtube_dl/extractor/scivee.py b/youtube_dl/extractor/scivee.py index 609a5ec99..33a78759a 100644 --- a/youtube_dl/extractor/scivee.py +++ b/youtube_dl/extractor/scivee.py @@ -11,13 +11,17 @@ class SciVeeIE(InfoExtractor): _TEST = { 'url': 'http://www.scivee.tv/node/62352', - 'md5': 'b16699b74c9e6a120f6772a44960304f', + #'md5': 'b16699b74c9e6a120f6772a44960304f', 'info_dict': { 'id': '62352', 'ext': 'mp4', 'title': 'Adam Arkin at the 2014 DOE JGI Genomics of Energy & Environment Meeting', 'description': 'md5:81f1710638e11a481358fab1b11059d7', - } + }, + 'params': { + # Range HTTP header is ignored + 'skip_download': True, + }, } def _real_extract(self, url): diff --git a/youtube_dl/extractor/syfy.py b/youtube_dl/extractor/syfy.py index 8809a57fe..f76b6e2b2 100644 --- a/youtube_dl/extractor/syfy.py +++ b/youtube_dl/extractor/syfy.py @@ -6,9 +6,9 @@ from .common import InfoExtractor class SyfyIE(InfoExtractor): - _VALID_URL = r'https?://www\.syfy\.com/videos/.+?vid:(?P<id>\d+)' + _VALID_URL = r'https?://www\.syfy\.com/(?:videos/.+?vid:(?P<id>[0-9]+)|(?!videos)(?P<video_name>[^/]+)(?:$|[?#]))' - _TEST = { + _TESTS = [{ 'url': 'http://www.syfy.com/videos/Robot%20Combat%20League/Behind%20the%20Scenes/vid:2631458', 'md5': 'e07de1d52c7278adbb9b9b1c93a66849', 'info_dict': { @@ -18,10 +18,30 @@ class SyfyIE(InfoExtractor): 'description': 'Listen to what insights George Lucas give his daughter Amanda.', }, 'add_ie': ['ThePlatform'], - } + }, { + 'url': 'http://www.syfy.com/wilwheaton', + 'md5': '94dfa54ee3ccb63295b276da08c415f6', + 'info_dict': { + 'id': '4yoffOOXC767', + 'ext': 'flv', + 'title': 'The Wil Wheaton Project - Premiering May 27th at 10/9c.', + 'description': 'The Wil Wheaton Project premieres May 27th at 10/9c. Don\'t miss it.', + }, + 'add_ie': ['ThePlatform'], + 'skip': 'Blocked outside the US', + }] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') + video_name = mobj.group('video_name') + if video_name: + generic_webpage = self._download_webpage(url, video_name) + video_id = self._search_regex( + r'<iframe.*?class="video_iframe_page"\s+src="/_utils/video/thP_video_controller.php.*?_vid([0-9]+)">', + generic_webpage, 'video ID') + url = 'http://www.syfy.com/videos/%s/%s/vid:%s' % ( + video_name, video_name, video_id) + else: + video_id = mobj.group('id') webpage = self._download_webpage(url, video_id) return self.url_result(self._og_search_video_url(webpage)) diff --git a/youtube_dl/extractor/theplatform.py b/youtube_dl/extractor/theplatform.py index 91f2453eb..f15780ef5 100644 --- a/youtube_dl/extractor/theplatform.py +++ b/youtube_dl/extractor/theplatform.py @@ -52,7 +52,7 @@ class ThePlatformIE(InfoExtractor): head = meta.find(_x('smil:head')) body = meta.find(_x('smil:body')) - f4m_node = body.find(_x('smil:seq/smil:video')) + f4m_node = body.find(_x('smil:seq//smil:video')) if f4m_node is not None: f4m_url = f4m_node.attrib['src'] if 'manifest.f4m?' not in f4m_url: |