New upstream release 2017.09.24.

[youtubedl] / youtube_dl / extractor / wsj.py

diff --git a/youtube_dl/extractor/wsj.py b/youtube_dl/extractor/wsj.py
index cbe3dc7bec5c982df8ec53431acdbb0fcd7e1d3a..9b5487710e9d1b73a2e26983bacde9e2e8891761 100644 (file)
--- a/youtube_dl/extractor/wsj.py
+++ b/youtube_dl/extractor/wsj.py
@@ -1,89 +1,120 @@
-# encoding: utf-8
+# coding: utf-8

 from __future__ import unicode_literals
 
 from .common import InfoExtractor
 from ..utils import (
     int_or_none,
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
 from ..utils import (
     int_or_none,

+    float_or_none,

     unified_strdate,
 )
 
 
 class WSJIE(InfoExtractor):
     unified_strdate,
 )
 
 
 class WSJIE(InfoExtractor):

-    _VALID_URL = r'https?://video-api\.wsj\.com/api-video/player/iframe\.html\?guid=(?P<id>[a-zA-Z0-9-]+)'
+    _VALID_URL = r'''(?x)
+                        (?:
+                            https?://video-api\.wsj\.com/api-video/player/iframe\.html\?.*?\bguid=|
+                            https?://(?:www\.)?(?:wsj|barrons)\.com/video/[^/]+/|
+                            wsj:
+                        )
+                        (?P<id>[a-fA-F0-9-]{36})
+                    '''

     IE_DESC = 'Wall Street Journal'
     IE_DESC = 'Wall Street Journal'

-    _TEST = {
+    _TESTS = [{

         'url': 'http://video-api.wsj.com/api-video/player/iframe.html?guid=1BD01A4C-BFE8-40A5-A42F-8A8AF9898B1A',
         'url': 'http://video-api.wsj.com/api-video/player/iframe.html?guid=1BD01A4C-BFE8-40A5-A42F-8A8AF9898B1A',

-        'md5': '9747d7a6ebc2f4df64b981e1dde9efa9',
+        'md5': 'e230a5bb249075e40793b655a54a02e4',

         'info_dict': {
             'id': '1BD01A4C-BFE8-40A5-A42F-8A8AF9898B1A',
             'ext': 'mp4',
             'upload_date': '20150202',
         'info_dict': {
             'id': '1BD01A4C-BFE8-40A5-A42F-8A8AF9898B1A',
             'ext': 'mp4',
             'upload_date': '20150202',

-            'uploader_id': 'bbright',
-            'creator': 'bbright',
+            'uploader_id': 'jdesai',
+            'creator': 'jdesai',

             'categories': list,  # a long list
             'duration': 90,
             'title': 'Bills Coach Rex Ryan Updates His Old Jets Tattoo',
         },
             'categories': list,  # a long list
             'duration': 90,
             'title': 'Bills Coach Rex Ryan Updates His Old Jets Tattoo',
         },

-    }
+    }, {
+        'url': 'http://www.wsj.com/video/can-alphabet-build-a-smarter-city/359DDAA8-9AC1-489C-82E6-0429C1E430E0.html',
+        'only_matching': True,
+    }, {
+        'url': 'http://www.barrons.com/video/capitalism-deserves-more-respect-from-millennials/F301217E-6F46-43AE-B8D2-B7180D642EE9.html',
+        'only_matching': True,
+    }]

 
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
 

-        bitrates = [128, 174, 264, 320, 464, 664, 1264]
-        api_url = (
-            'http://video-api.wsj.com/api-video/find_all_videos.asp?'
-            'type=guid&count=1&query=%s&'
-            'fields=hls,adZone,thumbnailList,guid,state,secondsUntilStartTime,'
-            'author,description,name,linkURL,videoStillURL,duration,videoURL,'
-            'adCategory,catastrophic,linkShortURL,doctypeID,youtubeID,'
-            'titletag,rssURL,wsj-section,wsj-subsection,allthingsd-section,'
-            'allthingsd-subsection,sm-section,sm-subsection,provider,'
-            'formattedCreationDate,keywords,keywordsOmniture,column,editor,'
-            'emailURL,emailPartnerID,showName,omnitureProgramName,'
-            'omnitureVideoFormat,linkRelativeURL,touchCastID,'
-            'omniturePublishDate,%s') % (
-                video_id, ','.join('video%dkMP4Url' % br for br in bitrates))
-        info = self._download_json(api_url, video_id)['items'][0]
-
-        # Thumbnails are conveniently in the correct format already
-        thumbnails = info.get('thumbnailList')
-        creator = info.get('author')
-        uploader_id = info.get('editor')
-        categories = info.get('keywords')
-        duration = int_or_none(info.get('duration'))
-        upload_date = unified_strdate(
-            info.get('formattedCreationDate'), day_first=False)
+        info = self._download_json(
+            'http://video-api.wsj.com/api-video/find_all_videos.asp', video_id,
+            query={
+                'type': 'guid',
+                'count': 1,
+                'query': video_id,
+                'fields': ','.join((
+                    'type', 'hls', 'videoMP4List', 'thumbnailList', 'author',
+                    'description', 'name', 'duration', 'videoURL', 'titletag',
+                    'formattedCreationDate', 'keywords', 'editor')),
+            })['items'][0]

         title = info.get('name', info.get('titletag'))
 
         title = info.get('name', info.get('titletag'))
 

-        formats = [{
-            'format_id': 'f4m',
-            'format_note': 'f4m (meta URL)',
-            'url': info['videoURL'],
-        }]
-        if info.get('hls'):
+        formats = []
+
+        f4m_url = info.get('videoURL')
+        if f4m_url:
+            formats.extend(self._extract_f4m_formats(
+                f4m_url, video_id, f4m_id='hds', fatal=False))
+
+        m3u8_url = info.get('hls')
+        if m3u8_url:

             formats.extend(self._extract_m3u8_formats(
                 info['hls'], video_id, ext='mp4',
             formats.extend(self._extract_m3u8_formats(
                 info['hls'], video_id, ext='mp4',

-                preference=0, entry_protocol='m3u8_native'))
-        for br in bitrates:
-            field = 'video%dkMP4Url' % br
-            if info.get(field):
-                formats.append({
-                    'format_id': 'mp4-%d' % br,
-                    'container': 'mp4',
-                    'tbr': br,
-                    'url': info[field],
-                })
+                entry_protocol='m3u8_native', m3u8_id='hls', fatal=False))
+
+        for v in info.get('videoMP4List', []):
+            mp4_url = v.get('url')
+            if not mp4_url:
+                continue
+            tbr = int_or_none(v.get('bitrate'))
+            formats.append({
+                'url': mp4_url,
+                'format_id': 'http' + ('-%d' % tbr if tbr else ''),
+                'tbr': tbr,
+                'width': int_or_none(v.get('width')),
+                'height': int_or_none(v.get('height')),
+                'fps': float_or_none(v.get('fps')),
+            })

         self._sort_formats(formats)
 
         return {
             'id': video_id,
             'formats': formats,
         self._sort_formats(formats)
 
         return {
             'id': video_id,
             'formats': formats,

-            'thumbnails': thumbnails,
-            'creator': creator,
-            'uploader_id': uploader_id,
-            'duration': duration,
-            'upload_date': upload_date,
+            # Thumbnails are conveniently in the correct format already
+            'thumbnails': info.get('thumbnailList'),
+            'creator': info.get('author'),
+            'uploader_id': info.get('editor'),
+            'duration': int_or_none(info.get('duration')),
+            'upload_date': unified_strdate(info.get(
+                'formattedCreationDate'), day_first=False),

             'title': title,
             'title': title,

-            'formats': formats,
-            'categories': categories,
+            'categories': info.get('keywords'),
+        }
+
+
+class WSJArticleIE(InfoExtractor):
+    _VALID_URL = r'(?i)https?://(?:www\.)?wsj\.com/articles/(?P<id>[^/?#&]+)'
+    _TEST = {
+        'url': 'https://www.wsj.com/articles/dont-like-china-no-pandas-for-you-1490366939?',
+        'info_dict': {
+            'id': '4B13FA62-1D8C-45DB-8EA1-4105CB20B362',
+            'ext': 'mp4',
+            'upload_date': '20170221',
+            'uploader_id': 'ralcaraz',
+            'title': 'Bao Bao the Panda Leaves for China',

         }
         }

+    }
+
+    def _real_extract(self, url):
+        article_id = self._match_id(url)
+        webpage = self._download_webpage(url, article_id)
+        video_id = self._search_regex(
+            r'data-src=["\']([a-fA-F0-9-]{36})', webpage, 'video id')
+        return self.url_result('wsj:%s' % video_id, WSJIE.ie_key(), video_id)