diff options
Diffstat (limited to 'youtube_dl/extractor')
-rw-r--r-- | youtube_dl/extractor/__init__.py | 2 | ||||
-rw-r--r-- | youtube_dl/extractor/cspan.py | 44 | ||||
-rw-r--r-- | youtube_dl/extractor/vevo.py | 1 | ||||
-rw-r--r-- | youtube_dl/extractor/wimp.py | 10 |
4 files changed, 52 insertions, 5 deletions
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 82927610a..2750fc8f9 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -6,6 +6,7 @@ from .bliptv import BlipTVIE, BlipTVUserIE from .breakcom import BreakIE from .collegehumor import CollegeHumorIE from .comedycentral import ComedyCentralIE +from .cspan import CSpanIE from .dailymotion import DailymotionIE from .depositfiles import DepositFilesIE from .eighttracks import EightTracksIE @@ -133,6 +134,7 @@ def gen_extractors(): VevoIE(), JukeboxIE(), TudouIE(), + CSpanIE(), WimpIE(), GenericIE() ] diff --git a/youtube_dl/extractor/cspan.py b/youtube_dl/extractor/cspan.py new file mode 100644 index 000000000..2246515f2 --- /dev/null +++ b/youtube_dl/extractor/cspan.py @@ -0,0 +1,44 @@ +import re + +from .common import InfoExtractor +from ..utils import ( + compat_urllib_parse, +) + +class CSpanIE(InfoExtractor): + _VALID_URL = r'http://www.c-spanvideo.org/program/(.*)' + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + prog_name = mobj.group(1) + webpage = self._download_webpage(url, prog_name) + video_id = self._search_regex(r'programid=(.*?)&', webpage, 'video id') + data = compat_urllib_parse.urlencode({'programid': video_id, + 'dynamic':'1'}) + info_url = 'http://www.c-spanvideo.org/common/services/flashXml.php?' + data + video_info = self._download_webpage(info_url, video_id, u'Downloading video info') + + self.report_extraction(video_id) + + title = self._html_search_regex(r'<string name="title">(.*?)</string>', + video_info, 'title') + description = self._html_search_regex(r'<meta (?:property="og:|name=")description" content="(.*?)"', + webpage, 'description', + flags=re.MULTILINE|re.DOTALL) + thumbnail = self._html_search_regex(r'<meta property="og:image" content="(.*?)"', + webpage, 'thumbnail') + + url = self._search_regex(r'<string name="URL">(.*?)</string>', + video_info, 'video url') + url = url.replace('$(protocol)', 'rtmp').replace('$(port)', '443') + path = self._search_regex(r'<string name="path">(.*?)</string>', + video_info, 'rtmp play path') + + return {'id': video_id, + 'title': title, + 'ext': 'flv', + 'url': url, + 'play_path': path, + 'description': description, + 'thumbnail': thumbnail, + } diff --git a/youtube_dl/extractor/vevo.py b/youtube_dl/extractor/vevo.py index aa88e1a92..49a249ae3 100644 --- a/youtube_dl/extractor/vevo.py +++ b/youtube_dl/extractor/vevo.py @@ -3,7 +3,6 @@ import json from .common import InfoExtractor from ..utils import ( - unified_strdate, ExtractorError, ) diff --git a/youtube_dl/extractor/wimp.py b/youtube_dl/extractor/wimp.py index a548e0fa0..84f065a3d 100644 --- a/youtube_dl/extractor/wimp.py +++ b/youtube_dl/extractor/wimp.py @@ -1,5 +1,6 @@ import re import base64 + from .common import InfoExtractor @@ -10,12 +11,13 @@ class WimpIE(InfoExtractor): mobj = re.match(self._VALID_URL, url) video_id = mobj.group(1) webpage = self._download_webpage(url, video_id) - title = self._search_regex('\<meta name\="description" content="(.+?)" \/\>',webpage, 'video title') - thumbnail_url = self._search_regex('\<meta property\=\"og\:image" content\=\"(.+?)\" />',webpage,'video thumbnail') - googleString = self._search_regex("googleCode = '(.*?)'", webpage,'file url') + title = self._search_regex(r'<meta name="description" content="(.+?)" />',webpage, 'video title') + thumbnail_url = self._search_regex(r'<meta property="og\:image" content="(.+?)" />', webpage,'video thumbnail') + googleString = self._search_regex("googleCode = '(.*?)'", webpage, 'file url') googleString = base64.b64decode(googleString).decode('ascii') final_url = self._search_regex('","(.*?)"', googleString,'final video url') - ext = final_url.split('.')[-1] + ext = final_url.rpartition(u'.')[2] + return [{ 'id': video_id, 'url': final_url, |