[hbo] Support episode pages (closes #10892)

diff --git a/ChangeLog b/ChangeLog
index 6c6053a2ad801e596eee97afacca9937751f7f09..d49682c8b1c5b23002310427c7b7aede3ee20aa5 100644 (file)
--- a/ChangeLog
+++ b/ChangeLog
@@ -4,6 +4,7 @@ Core
 * [Makefile] Support for GNU make < 4 is fixed; BSD make dropped (#9387)
 
 Extractors
++ [hbo] Add support for episode pages (#10892)
 * [allocine] Fix extraction (#10860)
 + [nextmedia] Recognize action news on AppleDaily
 

diff --git a/youtube_dl/extractor/hbo.py b/youtube_dl/extractor/hbo.py
index dad0f3994c93cd0a38a2be52741d7c55ce0e6749..3606d64fd0949ea7b5de2626dfffaf00151398e1 100644 (file)
--- a/youtube_dl/extractor/hbo.py
+++ b/youtube_dl/extractor/hbo.py
@@ -12,17 +12,7 @@ from ..utils import (
 )
 
 
-class HBOIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?hbo\.com/video/video\.html\?.*vid=(?P<id>[0-9]+)'
-    _TEST = {
-        'url': 'http://www.hbo.com/video/video.html?autoplay=true&g=u&vid=1437839',
-        'md5': '1c33253f0c7782142c993c0ba62a8753',
-        'info_dict': {
-            'id': '1437839',
-            'ext': 'mp4',
-            'title': 'Ep. 64 Clip: Encryption',
-        }
-    }
+class HBOBaseIE(InfoExtractor):
     _FORMATS_INFO = {
         '1920': {
             'width': 1280,
@@ -50,8 +40,7 @@ class HBOIE(InfoExtractor):
         },
     }
 
-    def _real_extract(self, url):
-        video_id = self._match_id(url)
+    def _extract_from_id(self, video_id):
         video_data = self._download_xml(
             'http://render.lv3.hbo.com/data/content/global/videos/data/%s.xml' % video_id, video_id)
         title = xpath_text(video_data, 'title', 'title', True)
@@ -116,7 +105,53 @@ class HBOIE(InfoExtractor):
         return {
             'id': video_id,
             'title': title,
-            'duration': parse_duration(xpath_element(video_data, 'duration/tv14')),
+            'duration': parse_duration(xpath_text(video_data, 'duration/tv14')),
             'formats': formats,
             'thumbnails': thumbnails,
         }
+
+
+class HBOIE(HBOBaseIE):
+    _VALID_URL = r'https?://(?:www\.)?hbo\.com/video/video\.html\?.*vid=(?P<id>[0-9]+)'
+    _TEST = {
+        'url': 'http://www.hbo.com/video/video.html?autoplay=true&g=u&vid=1437839',
+        'md5': '1c33253f0c7782142c993c0ba62a8753',
+        'info_dict': {
+            'id': '1437839',
+            'ext': 'mp4',
+            'title': 'Ep. 64 Clip: Encryption',
+            'thumbnail': 're:https?://.*\.jpg$',
+            'duration': 1072,
+        }
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        return self._extract_from_id(video_id)
+
+
+class HBOEpisodeIE(HBOBaseIE):
+    _VALID_URL = r'https?://(?:www\.)?hbo\.com/(?!video)([^/]+/)+video/(?P<id>[0-9a-z-]+)\.html'
+
+    _TESTS = [{
+        'url': 'http://www.hbo.com/girls/episodes/5/52-i-love-you-baby/video/ep-52-inside-the-episode.html?autoplay=true',
+        'md5': '689132b253cc0ab7434237fc3a293210',
+        'info_dict': {
+            'id': '1439518',
+            'ext': 'mp4',
+            'title': 'Ep. 52: Inside the Episode',
+            'thumbnail': 're:https?://.*\.jpg$',
+            'duration': 240,
+        },
+    }]
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, display_id)
+
+        video_id = self._search_regex(
+            r'(?P<q1>[\'"])videoId(?P=q1)\s*:\s*(?P<q2>[\'"])(?P<video_id>\d+)(?P=q2)',
+            webpage, 'video ID', group='video_id')
+
+        return self._extract_from_id(video_id)