[wsj] Add new extractor (Fixes #4854)

test/test_utils.py

@@ -156,6 +156,9 @@ class TestUtil(unittest.TestCase):
         self.assertEqual(
             unified_strdate('11/26/2014 11:30:00 AM PST', day_first=False),
             '20141126')
+        self.assertEqual(
+            unified_strdate('2/2/2015 6:47:40 PM', day_first=False),
+            '20150202')
 
     def test_find_xpath_attr(self):
         testxml = '''<root>

youtube_dl/extractor/__init__.py

@@ -554,6 +554,7 @@ from .wimp import WimpIE
 from .wistia import WistiaIE
 from .worldstarhiphop import WorldStarHipHopIE
 from .wrzuta import WrzutaIE
+from .wsj import WSJIE
 from .xbef import XBefIE
 from .xboxclips import XboxClipsIE
 from .xhamster import XHamsterIE

youtube_dl/extractor/common.py

@@ -145,6 +145,7 @@ class InfoExtractor(object):
     thumbnail:      Full URL to a video thumbnail image.
     description:    Full video description.
     uploader:       Full name of the video uploader.
+    creator:        The main artist who created the video.
     timestamp:      UNIX timestamp of the moment the video became available.
     upload_date:    Video upload date (YYYYMMDD).
                     If not explicitly set, calculated from timestamp.

youtube_dl/extractor/wsj.py

@@ -0,0 +1,89 @@
+# encoding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import (
+    int_or_none,
+    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-]+)'
+    IE_DESC = 'Wall Street Journal'
+    _TEST = {
+        'url': 'http://video-api.wsj.com/api-video/player/iframe.html?guid=1BD01A4C-BFE8-40A5-A42F-8A8AF9898B1A',
+        'md5': '9747d7a6ebc2f4df64b981e1dde9efa9',
+        'info_dict': {
+            'id': '1BD01A4C-BFE8-40A5-A42F-8A8AF9898B1A',
+            'ext': 'mp4',
+            'upload_date': '20150202',
+            'uploader_id': 'bbright',
+            'creator': 'bbright',
+            'categories': list,  # a long list
+            'duration': 90,
+            'title': 'Bills Coach Rex Ryan Updates His Old Jets Tattoo',
+        },
+    }
+
+    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)
+        title = info.get('name', info.get('titletag'))
+
+        formats = [{
+            'format_id': 'f4m',
+            'format_note': 'f4m (meta URL)',
+            'url': info['videoURL'],
+        }]
+        if info.get('hls'):
+            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],
+                })
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'formats': formats,
+            'thumbnails': thumbnails,
+            'creator': creator,
+            'uploader_id': uploader_id,
+            'duration': duration,
+            'upload_date': upload_date,
+            'title': title,
+            'formats': formats,
+            'categories': categories,
+        }

youtube_dl/utils.py

@@ -701,7 +701,7 @@ def unified_strdate(date_str, day_first=True):
     # %z (UTC offset) is only supported in python>=3.2
     date_str = re.sub(r' ?(\+|-)[0-9]{2}:?[0-9]{2}$', '', date_str)
     # Remove AM/PM + timezone
-    date_str = re.sub(r'(?i)\s*(?:AM|PM)\s+[A-Z]+', '', date_str)
+    date_str = re.sub(r'(?i)\s*(?:AM|PM)(?:\s+[A-Z]+)?', '', date_str)
 
     format_expressions = [
         '%d %B %Y',