]> git.bitcoin.ninja Git - youtube-dl/commitdiff
[baiduvideo] Add new extractor (closes #4563)
authorYen Chi Hsuan <yan12125@gmail.com>
Sat, 2 May 2015 16:51:24 +0000 (00:51 +0800)
committerYen Chi Hsuan <yan12125@gmail.com>
Sat, 2 May 2015 16:53:24 +0000 (00:53 +0800)
youtube_dl/extractor/__init__.py
youtube_dl/extractor/baidu.py [new file with mode: 0644]

index 43f3e680829d22d46ec4d4214a0aaff9a46875a6..41af925ccab47d183c3d5df347ccce7dc62e393b 100644 (file)
@@ -32,6 +32,7 @@ from .atresplayer import AtresPlayerIE
 from .atttechchannel import ATTTechChannelIE
 from .audiomack import AudiomackIE, AudiomackAlbumIE
 from .azubu import AzubuIE
+from .baidu import BaiduVideoIE
 from .bambuser import BambuserIE, BambuserChannelIE
 from .bandcamp import BandcampIE, BandcampAlbumIE
 from .bbccouk import BBCCoUkIE
diff --git a/youtube_dl/extractor/baidu.py b/youtube_dl/extractor/baidu.py
new file mode 100644 (file)
index 0000000..7f7a88f
--- /dev/null
@@ -0,0 +1,68 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..compat import compat_urlparse
+
+
+class BaiduVideoIE(InfoExtractor):
+    _VALID_URL = r'http://v\.baidu\.com/(?P<type>[a-z]+)/(?P<id>\d+).htm'
+    _TESTS = [{
+        'url': 'http://v.baidu.com/comic/1069.htm?frp=bdbrand&q=%E4%B8%AD%E5%8D%8E%E5%B0%8F%E5%BD%93%E5%AE%B6',
+        'info_dict': {
+            'id': '1069',
+            'title': '中华小当家 TV版 (全52集)',
+            'description': 'md5:395a419e41215e531c857bb037bbaf80',
+        },
+        'playlist_count': 52,
+    }, {
+        'url': 'http://v.baidu.com/show/11595.htm?frp=bdbrand',
+        'info_dict': {
+            'id': '11595',
+            'title': 're:^奔跑吧兄弟',
+            'description': 'md5:1bf88bad6d850930f542d51547c089b8',
+        },
+        'playlist_mincount': 3,
+    }]
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        playlist_id = mobj.group('id')
+        category = category2 = mobj.group('type')
+        if category == 'show':
+            category2 = 'tvshow'
+
+        webpage = self._download_webpage(url, playlist_id)
+
+        playlist_title = self._html_search_regex(
+            r'title\s*:\s*(["\'])(?P<title>[^\']+)\1', webpage,
+            'playlist title', group='title')
+        playlist_description = self._html_search_regex(
+            r'<input[^>]+class="j-data-intro"[^>]+value="([^"]+)"/>', webpage,
+            playlist_id, 'playlist description')
+
+        site = self._html_search_regex(
+            r'filterSite\s*:\s*["\']([^"]*)["\']', webpage,
+            'primary provider site')
+        api_result = self._download_json(
+            'http://v.baidu.com/%s_intro/?dtype=%sPlayUrl&id=%s&site=%s' % (
+                category, category2, playlist_id, site),
+            playlist_id, 'Get playlist links')
+
+        entries = []
+        for episode in api_result[0]['episodes']:
+            episode_id = '%s_%s' % (playlist_id, episode['episode'])
+
+            redirect_page = self._download_webpage(
+                compat_urlparse.urljoin(url, episode['url']), episode_id,
+                note='Download Baidu redirect page')
+            real_url = self._html_search_regex(
+                r'location\.replace\("([^"]+)"\)', redirect_page, 'real URL')
+
+            entries.append(self.url_result(
+                real_url, video_title=episode['single_title']))
+
+        return self.playlist_result(
+            entries, playlist_id, playlist_title, playlist_description)