[ellentv] Add new extractor

diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py
index 2ea2c73d24c734901fb1a03a7e8b3be473099509..381a5d999c2b011bc925082a9440ff444dd9e9a1 100644 (file)
--- a/youtube_dl/extractor/__init__.py
+++ b/youtube_dl/extractor/__init__.py
@@ -77,6 +77,10 @@ from .ebaumsworld import EbaumsWorldIE
 from .ehow import EHowIE
 from .eighttracks import EightTracksIE
 from .eitb import EitbIE
+from .ellentv import (
+    EllenTVIE,
+    EllenTVClipsIE,
+)
 from .elpais import ElPaisIE
 from .empflix import EmpflixIE
 from .engadget import EngadgetIE

diff --git a/youtube_dl/extractor/ellentv.py b/youtube_dl/extractor/ellentv.py
new file mode 100644 (file)
index 0000000..933f36d
--- /dev/null
+++ b/youtube_dl/extractor/ellentv.py
@@ -0,0 +1,79 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+import json
+
+from .common import InfoExtractor, ExtractorError
+
+class EllenTVIE(InfoExtractor):
+    IE_NAME = u'ellentv'
+    _VALID_URL = r'https?://(?:www\.)?ellentv\.com/videos/(?P<id>[a-z0-9_-]+)'
+    _TEST = {
+        'url': 'http://www.ellentv.com/videos/0-7jqrsr18/',
+        'md5': 'e4af06f3bf0d5f471921a18db5764642',
+        'info_dict': {
+            'id': '0-7jqrsr18',
+            'ext': 'mp4',
+            'title': u'What\'s Wrong with These Photos? A Whole Lot',
+            # TODO more properties, either as:
+            # * A value
+            # * MD5 checksum; start the string with md5:
+            # * A regular expression; start the string with re:
+            # * Any Python type (for example int or float)
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        id = mobj.group('id')
+
+        webpage = self._download_webpage(url, id)
+
+        return {
+            'id': id,
+            'title': self._og_search_title(webpage),
+            'url': self._html_search_meta('VideoURL', webpage, 'url')
+        }
+
+class EllenTVClipsIE(InfoExtractor):
+    IE_NAME = u'ellentv:clips'
+    _VALID_URL = r'https?://(?:www\.)?ellentv\.com/episodes/(?P<id>[a-z0-9_-]+)'
+    _TEST = {
+        'url': 'http://www.ellentv.com/episodes/meryl-streep-vanessa-hudgens/',
+        'md5': 'TODO: md5 sum of the first 10KiB of the video file',
+        'info_dict': {
+            'id': '0_wf6pizq7',
+            'ext': 'mp4',
+            'title': 'Video title goes here',
+            # TODO more properties, either as:
+            # * A value
+            # * MD5 checksum; start the string with md5:
+            # * A regular expression; start the string with re:
+            # * Any Python type (for example int or float)
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        playlist_id = mobj.group('id')
+
+        webpage = self._download_webpage(url, playlist_id)
+        playlist = self._extract_playlist(webpage)
+
+        return {
+            '_type': 'playlist',
+            'id': playlist_id,
+            'title': self._og_search_title(webpage),
+            'entries': self._extract_entries(playlist)
+        }
+
+    def _extract_playlist(self, webpage):
+        json_string = self._search_regex(r'playerView.addClips\(\[\{(.*?)\}\]\);', webpage, 'json')
+        try:
+            return json.loads("[{" + json_string + "}]")
+        except ValueError as ve:
+            raise ExtractorError('Failed to download JSON', cause=ve)
+
+    def _extract_entries(self, playlist):
+        return [self.url_result(item[u'url'], 'EllenTV') for item in playlist]