[OdaTV] Add new extractor

youtube_dl/extractor/extractors.py

@@ -542,6 +542,7 @@ from .nytimes import (
     NYTimesArticleIE,
 )
 from .nuvid import NuvidIE
+from .odatv import OdaTVIE
 from .odnoklassniki import OdnoklassnikiIE
 from .oktoberfesttv import OktoberfestTVIE
 from .onionstudios import OnionStudiosIE

youtube_dl/extractor/odatv.py

@@ -0,0 +1,60 @@
+# coding: utf-8
+
+from __future__ import unicode_literals
+from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+    remove_start
+)
+import re
+
+
+class OdaTVIE(InfoExtractor):
+    _VALID_URL = r'^https?://(?:www\.)?odatv\.com/(?:mob|vid)_video\.php\?id=(?P<id>[^&]*)'
+    _TESTS = [{
+        'url': 'http://odatv.com/vid_video.php?id=8E388',
+        'md5': 'dc61d052f205c9bf2da3545691485154',
+        'info_dict': {
+            'id': '8E388',
+            'ext': 'mp4',
+            'title': 'md5:69654805a16a16cf9ec9d055e079831c'
+        }
+    }, {
+        'url': 'http://odatv.com/mob_video.php?id=8E388',
+        'md5': 'dc61d052f205c9bf2da3545691485154',
+        'info_dict': {
+            'id': '8E388',
+            'ext': 'mp4',
+            'title': 'md5:69654805a16a16cf9ec9d055e079831c'
+        }
+    }, {
+        'url': 'http://odatv.com/mob_video.php?id=8E900',
+        'md5': '',
+        'info_dict': {
+            'id': '8E900',
+            'ext': 'mp4',
+            'title': 'not found check'
+        }
+    }, {
+        'url': 'http://odatv.com/mob_video.php?id=8E395',
+        'md5': '13179a1025f07b60933d311e06574a70',
+        'info_dict': {
+            'id': '8E395',
+            'ext': 'mp4',
+            'title': 'md5:16d2e8d0eb42e793d8224af3fae20c86'
+        }
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+        print(url)
+        if 'NO VIDEO!' in webpage:
+            raise ExtractorError('Video %s does not exist' % video_id, expected=True)
+
+        return {
+            'id': video_id,
+            'title': remove_start(self._og_search_title(webpage), 'Video: '),
+            'thumbnail': self._og_search_thumbnail(webpage),
+            'url': self._html_search_regex(r"(http.+?video_%s\.mp4)" % re.escape(video_id), webpage, 'url', flags=re.IGNORECASE)
+        }