youtube-dl

commit aa0c87391c7b84cde2fa8e307ffe5329e8ed3e5b
parent 2e3252801219dc82c379ba00a30c629039b06a24
Author: Jaime Marquínez Ferrándiz <jaime.marquinez.ferrandiz@gmail.com>
Date:   Wed, 26 Jun 2013 17:55:54 +0200

Add CSpanIE (closes #312)

Diffstat:
M
test/tests.json
 | 
10
++++++++++
M
youtube_dl/extractor/__init__.py
 | 
2
++
A
youtube_dl/extractor/cspan.py
 | 
44
++++++++++++++++++++++++++++++++++++++++++++

3 files changed, 56 insertions(+), 0 deletions(-)
diff --git a/test/tests.json b/test/tests.json
@@ -695,5 +695,15 @@
     "info_dict": {
         "title": "卡马乔国足开大脚长传冲吊集锦"
     }
+  },
+  {
+    "name": "CSpan",
+    "url": "http://www.c-spanvideo.org/program/HolderonV",
+    "file": "315139.flv",
+    "md5": "74a623266956f69e4df0068ab6c80fe4",
+    "info_dict": {
+        "title": "Attorney General Eric Holder on Voting Rights Act Decision"
+    },
+    "skip": "Requires rtmpdump"
   }
 ]
diff --git 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
@@ -132,6 +133,7 @@ def gen_extractors():
         VevoIE(),
         JukeboxIE(),
         TudouIE(),
+        CSpanIE(),
         GenericIE()
     ]
 
diff --git a/youtube_dl/extractor/cspan.py 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,
+                }