[tvp] Telewizja Polska: new extractor for tvp.pl, fixes #1719
authorMarcin Cieślak <saper@saper.info>
Tue, 5 Nov 2013 22:30:25 +0000 (23:30 +0100)
committerMarcin Cieślak <saper@saper.info>
Tue, 5 Nov 2013 22:47:40 +0000 (23:47 +0100)
Thanks-To: mplonski

https://github.com/mplonski/linux/blob/master/tvp-dl.py

youtube_dl/extractor/__init__.py
youtube_dl/extractor/tvp.py [new file with mode: 0644]

index 888a91ccedc2900ddf1e3e6bf3d385ad6adb1b27..78f84cea3b9002f394f6ed13da8faae2da59baeb 100644 (file)
@@ -132,6 +132,7 @@ from .tube8 import Tube8IE
 from .tudou import TudouIE
 from .tumblr import TumblrIE
 from .tutv import TutvIE
+from .tvp import TvpIE
 from .unistra import UnistraIE
 from .ustream import UstreamIE, UstreamChannelIE
 from .vbox7 import Vbox7IE
diff --git a/youtube_dl/extractor/tvp.py b/youtube_dl/extractor/tvp.py
new file mode 100644 (file)
index 0000000..63fb57b
--- /dev/null
@@ -0,0 +1,60 @@
+# encoding: utf-8
+import re
+import json
+
+from .common import InfoExtractor
+from ..utils import (
+    determine_ext,
+    ExtractorError,
+    RegexNotFoundError,
+)
+
+class TvpIE(InfoExtractor):
+    IE_NAME = u'tvp.pl'
+    _VALID_URL = r'https?://www\.tvp\.pl/.*?wideo/(?P<date>\d+)/(?P<id>\d+)'
+    _INFO_URL = 'http://www.tvp.pl/pub/stat/videofileinfo?video_id=%s'
+
+
+    _TEST = {
+        u'url': u'http://www.tvp.pl/warszawa/magazyny/campusnews/wideo/31102013/12878238',
+        u'file': u'31.10.2013-12878238.wmv',
+        u'info_dict': {
+            u'title': u'31.10.2013',
+            u'description': u'31.10.2013',
+        },
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+        webpage = self._download_webpage(url, video_id, "Downloading video webpage")
+        json_params = self._download_webpage(self._INFO_URL % video_id, video_id, "Downloading video metadata")
+
+        try:
+            params = json.loads(json_params)
+        except:
+            raise ExtractorError(u'Invalid JSON')
+
+        self.report_extraction(video_id)
+        try:
+            video_url = params['video_url']
+        except KeyError:
+            raise ExtractorError('Missing JSON parameter: ' + sys.exc_info()[1])
+
+        try:
+            title = self._og_search_title(webpage)
+        except RegexNotFoundError:
+            title = video_id
+        info = {
+            'id': video_id,
+            'title': title,
+            'ext': 'wmv',
+            'url': video_url,
+        }
+        try:
+            info['description'] = self._og_search_description(webpage)
+            info['thumbnail'] = self._og_search_thumbnail(webpage)
+        except RegexNotFoundError:
+            pass
+
+        return info