youtube-dl

commit 594601f54570b8e79606002b6342dd5fcdc1f133
parent 0ae9560eea3e829fdb9daefac027e5c983e4db98
Author: ping <lipng.ong@gmail.com>
Date:   Tue, 27 Sep 2016 13:29:21 +0800

[ondemandkorea] Add extractor

Diffstat:
M
youtube_dl/extractor/extractors.py
 | 
1
+
A
youtube_dl/extractor/ondemandkorea.py
 | 
58
++++++++++++++++++++++++++++++++++++++++++++++++++++++++++

2 files changed, 59 insertions(+), 0 deletions(-)
diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py
@@ -662,6 +662,7 @@ from .nzz import NZZIE
 from .odatv import OdaTVIE
 from .odnoklassniki import OdnoklassnikiIE
 from .oktoberfesttv import OktoberfestTVIE
+from .ondemandkorea import OnDemandKoreaIE
 from .onet import (
     OnetIE,
     OnetChannelIE,
diff --git a/youtube_dl/extractor/ondemandkorea.py b/youtube_dl/extractor/ondemandkorea.py
@@ -0,0 +1,58 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import json
+import re
+
+from .common import InfoExtractor
+from ..utils import ExtractorError
+
+
+class OnDemandKoreaIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?ondemandkorea\.com/(?P<id>[^/]+)\.html'
+    _TEST = {
+        'url': 'http://www.ondemandkorea.com/ask-us-anything-e43.html',
+        'info_dict': {
+            'id': 'ask-us-anything-e43',
+            'ext': 'mp4',
+            'title': 'Ask Us Anything : E43',
+            'thumbnail': 're:^https?://.*\.jpg$',
+        },
+        'params': {
+            'skip_download': 'm3u8 download'
+        }
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id, fatal=False)
+
+        if not webpage:
+            # Page sometimes returns captcha page with HTTP 403
+            raise ExtractorError('Unable to access page. You may have been blocked.', expected=True)
+
+        if 'msg_block_01.png' in webpage:
+            raise ExtractorError('This content is not available in your region.', expected=True)
+        
+        if 'This video is only available to ODK PLUS members.' in webpage:
+            raise ExtractorError('This video is only available to ODK PLUS members.', expected=True)
+
+        title = self._og_search_title(webpage)
+        thumbnail = self._og_search_thumbnail(webpage)
+
+        manifest_url = self._search_regex(r'file:\s"(https?://[\S].+?/manifest\.m3u8)', webpage, 'manifest')
+        formats = self._extract_m3u8_formats(manifest_url, video_id, 'mp4', m3u8_id='hls')
+        self._sort_formats(formats)
+
+        subs = re.findall(r'file:\s\'(?P<file>[^\']+\.vtt)\',\s+label:\s+\'(?P<lang>[^\']+)\'', webpage)
+        subtitles = {}
+        for sub in subs:
+            subtitles[sub[1]] = [{'url': 'http://www.ondemandkorea.com' + sub[0], 'ext': sub[0][-3:]}]
+
+        return {
+            'id': video_id,
+            'title': title,
+            'thumbnail': thumbnail,
+            'formats': formats,
+            'subtitles': subtitles,
+        }