youtube-dl

commit 0a477f873115a11dbaadae674c2aaabe15ec4249
parent 7f4173ae7c0dae870250018cd4915df36ccf0f54
Author: Sergey M․ <dstftw@gmail.com>
Date:   Sun, 13 Mar 2016 17:22:23 +0600

[vice:show] Add extractor (Closes #8847)

Diffstat:
M
youtube_dl/extractor/__init__.py
 | 
5
++++-
M
youtube_dl/extractor/vice.py
 | 
78
++++++++++++++++++++++++++++++++++++++++++++++++++++++++++--------------------

2 files changed, 62 insertions(+), 21 deletions(-)
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py
@@ -836,7 +836,10 @@ from .vgtv import (
     VGTVIE,
 )
 from .vh1 import VH1IE
-from .vice import ViceIE
+from .vice import (
+    ViceIE,
+    ViceShowIE,
+)
 from .viddler import ViddlerIE
 from .videodetective import VideoDetectiveIE
 from .videofyme import VideofyMeIE
diff --git a/youtube_dl/extractor/vice.py b/youtube_dl/extractor/vice.py
@@ -1,31 +1,37 @@
 from __future__ import unicode_literals
 
+import re
+
 from .common import InfoExtractor
 from .ooyala import OoyalaIE
 from ..utils import ExtractorError
 
 
 class ViceIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:.+?\.)?vice\.com/(?:[^/]+/)+(?P<id>.+)'
-
-    _TESTS = [
-        {
-            'url': 'http://www.vice.com/Fringes/cowboy-capitalists-part-1',
-            'info_dict': {
-                'id': '43cW1mYzpia9IlestBjVpd23Yu3afAfp',
-                'ext': 'mp4',
-                'title': 'VICE_COWBOYCAPITALISTS_PART01_v1_VICE_WM_1080p.mov',
-                'duration': 725.983,
-            },
-            'params': {
-                # Requires ffmpeg (m3u8 manifest)
-                'skip_download': True,
-            },
-        }, {
-            'url': 'https://news.vice.com/video/experimenting-on-animals-inside-the-monkey-lab',
-            'only_matching': True,
-        }
-    ]
+    _VALID_URL = r'https?://(?:.+?\.)?vice\.com/(?:[^/]+/)?videos?/(?P<id>[^/?#&]+)'
+
+    _TESTS = [{
+        'url': 'http://www.vice.com/video/cowboy-capitalists-part-1',
+        'info_dict': {
+            'id': '43cW1mYzpia9IlestBjVpd23Yu3afAfp',
+            'ext': 'mp4',
+            'title': 'VICE_COWBOYCAPITALISTS_PART01_v1_VICE_WM_1080p.mov',
+            'duration': 725.983,
+        },
+        'params': {
+            # Requires ffmpeg (m3u8 manifest)
+            'skip_download': True,
+        },
+    }, {
+        'url': 'https://news.vice.com/video/experimenting-on-animals-inside-the-monkey-lab',
+        'only_matching': True,
+    }, {
+        'url': 'http://www.vice.com/ru/video/big-night-out-ibiza-clive-martin-229',
+        'only_matching': True,
+    }, {
+        'url': 'https://munchies.vice.com/en/videos/watch-the-trailer-for-our-new-series-the-pizza-show',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
@@ -38,3 +44,35 @@ class ViceIE(InfoExtractor):
         except ExtractorError:
             raise ExtractorError('The page doesn\'t contain a video', expected=True)
         return self.url_result(ooyala_url, ie='Ooyala')
+
+
+class ViceShowIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:.+?\.)?vice\.com/(?:[^/]+/)?show/(?P<id>[^/?#&]+)'
+
+    _TEST = {
+        'url': 'https://munchies.vice.com/en/show/fuck-thats-delicious-2',
+        'info_dict': {
+            'id': 'fuck-thats-delicious-2',
+            'title': "Fuck, That's Delicious",
+            'description': 'Follow the culinary adventures of rapper Action Bronson during his ongoing world tour.',
+        },
+        'playlist_count': 17,
+    }
+
+    def _real_extract(self, url):
+        show_id = self._match_id(url)
+        webpage = self._download_webpage(url, show_id)
+
+        entries = [
+            self.url_result(video_url, ViceIE.ie_key())
+            for video_url, _ in re.findall(
+                r'<h2[^>]+class="article-title"[^>]+data-id="\d+"[^>]*>\s*<a[^>]+href="(%s.*?)"'
+                % ViceIE._VALID_URL, webpage)]
+
+        title = self._search_regex(
+            r'<title>(.+?)</title>', webpage, 'title', default=None)
+        if title:
+            title = re.sub(r'(.+)\s*\|\s*.+$', r'\1', title).strip()
+        description = self._html_search_meta('description', webpage, 'description')
+
+        return self.playlist_result(entries, show_id, title, description)