Merge pull request #1 from e7appew/python3

[youtubedl] / youtube_dl / extractor / vice.py

diff --git a/youtube_dl/extractor/vice.py b/youtube_dl/extractor/vice.py
index 04e2b0ba7849adee473a42e471d77ced7df0652c..e2b2ce0981cc8767ade2f5ef4c8bc52759b86af3 100644 (file)
--- a/youtube_dl/extractor/vice.py
+++ b/youtube_dl/extractor/vice.py
@@ -1,36 +1,91 @@
 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'http://www\.vice\.com/.*?/(?P<name>.+)'
+    _VALID_URL = r'https?://(?:.+?\.)?vice\.com/(?:[^/]+/)?videos?/(?P<id>[^/?#&]+)'
 
-    _TEST = {
-        'url': 'http://www.vice.com/Fringes/cowboy-capitalists-part-1',
+    _TESTS = [{
+        'url': 'http://www.vice.com/video/cowboy-capitalists-part-1',
+        'md5': 'e9d77741f9e42ba583e683cd170660f7',
         'info_dict': {
             'id': '43cW1mYzpia9IlestBjVpd23Yu3afAfp',
-            'ext': 'mp4',
+            'ext': 'flv',
             'title': 'VICE_COWBOYCAPITALISTS_PART01_v1_VICE_WM_1080p.mov',
+            'duration': 725.983,
         },
-        'params': {
-            # Requires ffmpeg (m3u8 manifest)
-            'skip_download': True,
+        'add_ie': ['Ooyala'],
+    }, {
+        'url': 'http://www.vice.com/video/how-to-hack-a-car',
+        'md5': '6fb2989a3fed069fb8eab3401fc2d3c9',
+        'info_dict': {
+            'id': '3jstaBeXgAs',
+            'ext': 'mp4',
+            'title': 'How to Hack a Car: Phreaked Out (Episode 2)',
+            'description': 'md5:ee95453f7ff495db8efe14ae8bf56f30',
+            'uploader_id': 'MotherboardTV',
+            'uploader': 'Motherboard',
+            'upload_date': '20140529',
         },
-    }
+        'add_ie': ['Youtube'],
+    }, {
+        '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):
-        mobj = re.match(self._VALID_URL, url)
-        name = mobj.group('name')
-        webpage = self._download_webpage(url, name)
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
         try:
             embed_code = self._search_regex(
                 r'embedCode=([^&\'"]+)', webpage,
-                'ooyala embed code')
-            ooyala_url = OoyalaIE._url_for_embed_code(embed_code)
+                'ooyala embed code', default=None)
+            if embed_code:
+                return self.url_result('ooyala:%s' % embed_code, 'Ooyala')
+            youtube_id = self._search_regex(
+                r'data-youtube-id="([^"]+)"', webpage, 'youtube id')
+            return self.url_result(youtube_id, 'Youtube')
         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)