diff options
author | Sergey M․ <dstftw@gmail.com> | 2014-09-28 02:32:52 +0700 |
---|---|---|
committer | Sergey M․ <dstftw@gmail.com> | 2014-09-28 02:32:52 +0700 |
commit | b3ac3a51ac8c4a00186ef525253354eaaca0a553 (patch) | |
tree | 3dfc0966198be84dd15257a57206884381a84a45 /youtube_dl | |
parent | 2f9e8776df664e21aee18b05c468a56b03fe4417 (diff) | |
parent | 0b75c2a88ba56a84322db6cc1a298d7e52b44b2a (diff) | |
download | youtube-dl-b3ac3a51ac8c4a00186ef525253354eaaca0a553.tar.xz |
Merge branch 'lenaten-sport5'
Diffstat (limited to 'youtube_dl')
-rwxr-xr-x | youtube_dl/YoutubeDL.py | 5 | ||||
-rw-r--r-- | youtube_dl/extractor/__init__.py | 1 | ||||
-rw-r--r-- | youtube_dl/extractor/sport5.py | 92 |
3 files changed, 96 insertions, 2 deletions
diff --git a/youtube_dl/YoutubeDL.py b/youtube_dl/YoutubeDL.py index a1713dc5a..b485dbdf1 100755 --- a/youtube_dl/YoutubeDL.py +++ b/youtube_dl/YoutubeDL.py @@ -1250,12 +1250,13 @@ class YoutubeDL(object): # urllib chokes on URLs with non-ASCII characters (see http://bugs.python.org/issue3991) # To work around aforementioned issue we will replace request's original URL with # percent-encoded one - url = req if isinstance(req, compat_str) else req.get_full_url() + req_is_string = isinstance(req, basestring) + url = req if req_is_string else req.get_full_url() url_escaped = escape_url(url) # Substitute URL if any change after escaping if url != url_escaped: - if isinstance(req, compat_str): + if req_is_string: req = url_escaped else: req = compat_urllib_request.Request( diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 1f1fc0eb2..c3a4d3c9a 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -340,6 +340,7 @@ from .spiegel import SpiegelIE, SpiegelArticleIE from .spiegeltv import SpiegeltvIE from .spike import SpikeIE from .sportdeutschland import SportDeutschlandIE +from .sport5 import Sport5IE from .stanfordoc import StanfordOpenClassroomIE from .steam import SteamIE from .streamcloud import StreamcloudIE diff --git a/youtube_dl/extractor/sport5.py b/youtube_dl/extractor/sport5.py new file mode 100644 index 000000000..3f680bfc6 --- /dev/null +++ b/youtube_dl/extractor/sport5.py @@ -0,0 +1,92 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ExtractorError + + +class Sport5IE(InfoExtractor): + _VALID_URL = r'http://(?:www|vod)?\.sport5\.co\.il/.*\b(?:Vi|docID)=(?P<id>\d+)' + _TESTS = [ + { + 'url': 'http://vod.sport5.co.il/?Vc=147&Vi=176331&Page=1', + 'info_dict': { + 'id': 's5-Y59xx1-GUh2', + 'ext': 'mp4', + 'title': 'ולנסיה-קורדובה 0:3', + 'description': 'אלקאסר, גאייה ופגולי סידרו לקבוצה של נונו ניצחון על קורדובה ואת המקום הראשון בליגה', + 'duration': 228, + 'categories': list, + }, + 'skip': 'Blocked outside of Israel', + }, { + 'url': 'http://www.sport5.co.il/articles.aspx?FolderID=3075&docID=176372&lang=HE', + 'info_dict': { + 'id': 's5-SiXxx1-hKh2', + 'ext': 'mp4', + 'title': 'GOALS_CELTIC_270914.mp4', + 'description': '', + 'duration': 87, + 'categories': list, + }, + 'skip': 'Blocked outside of Israel', + } + ] + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + media_id = mobj.group('id') + + webpage = self._download_webpage(url, media_id) + + video_id = self._html_search_regex('clipId=([\w-]+)', webpage, 'video id') + + metadata = self._download_xml( + 'http://sport5-metadata-rr-d.nsacdn.com/vod/vod/%s/HDS/metadata.xml' % video_id, + video_id) + + error = metadata.find('./Error') + if error is not None: + raise ExtractorError( + '%s returned error: %s - %s' % ( + self.IE_NAME, + error.find('./Name').text, + error.find('./Description').text), + expected=True) + + title = metadata.find('./Title').text + description = metadata.find('./Description').text + duration = int(metadata.find('./Duration').text) + + posters_el = metadata.find('./PosterLinks') + thumbnails = [{ + 'url': thumbnail.text, + 'width': int(thumbnail.get('width')), + 'height': int(thumbnail.get('height')), + } for thumbnail in posters_el.findall('./PosterIMG')] if posters_el is not None else [] + + categories_el = metadata.find('./Categories') + categories = [ + cat.get('name') for cat in categories_el.findall('./Category') + ] if categories_el is not None else [] + + formats = [{ + 'url': fmt.text, + 'ext': 'mp4', + 'vbr': int(fmt.get('bitrate')), + 'width': int(fmt.get('width')), + 'height': int(fmt.get('height')), + } for fmt in metadata.findall('./PlaybackLinks/FileURL')] + self._sort_formats(formats) + + return { + 'id': video_id, + 'title': title, + 'description': description, + 'thumbnails': thumbnails, + 'duration': duration, + 'categories': categories, + 'formats': formats, + }
\ No newline at end of file |