diff options
| -rw-r--r-- | youtube_dl/extractor/generic.py | 7 | ||||
| -rw-r--r-- | youtube_dl/extractor/nytimes.py | 33 |
2 files changed, 25 insertions, 15 deletions
diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index dc5755d12..8716e4503 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -1006,6 +1006,13 @@ class GenericIE(InfoExtractor): if mobj is not None: return self.url_result(mobj.group('url')) + # Look for NYTimes player + mobj = re.search( + r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>', + webpage) + if mobj is not None: + return self.url_result(mobj.group('url')) + # Look for Ooyala videos mobj = (re.search(r'player\.ooyala\.com/[^"?]+\?[^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or diff --git a/youtube_dl/extractor/nytimes.py b/youtube_dl/extractor/nytimes.py index 56e1cad3b..d1cf8f4f3 100644 --- a/youtube_dl/extractor/nytimes.py +++ b/youtube_dl/extractor/nytimes.py @@ -1,13 +1,15 @@ from __future__ import unicode_literals -import re - from .common import InfoExtractor -from ..utils import parse_iso8601 +from ..utils import ( + float_or_none, + int_or_none, + parse_iso8601, +) class NYTimesIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?nytimes\.com/video/(?:[^/]+/)+(?P<id>\d+)' + _VALID_URL = r'https?://(?:(?:www\.)?nytimes\.com/video/(?:[^/]+/)+|graphics8\.nytimes\.com/bcvideo/\d+(?:\.\d+)?/iframe/embed\.html\?videoId=)(?P<id>\d+)' _TEST = { 'url': 'http://www.nytimes.com/video/opinion/100000002847155/verbatim-what-is-a-photocopier.html?playlistId=100000001150263', @@ -25,15 +27,15 @@ class NYTimesIE(InfoExtractor): } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') + video_id = self._match_id(url) video_data = self._download_json( - 'http://www.nytimes.com/svc/video/api/v2/video/%s' % video_id, video_id, 'Downloading video JSON') + 'http://www.nytimes.com/svc/video/api/v2/video/%s' % video_id, + video_id, 'Downloading video JSON') title = video_data['headline'] - description = video_data['summary'] - duration = video_data['duration'] / 1000.0 + description = video_data.get('summary') + duration = float_or_none(video_data.get('duration'), 1000) uploader = video_data['byline'] timestamp = parse_iso8601(video_data['publication_date'][:-8]) @@ -49,11 +51,11 @@ class NYTimesIE(InfoExtractor): formats = [ { 'url': video['url'], - 'format_id': video['type'], - 'vcodec': video['video_codec'], - 'width': video['width'], - 'height': video['height'], - 'filesize': get_file_size(video['fileSize']), + 'format_id': video.get('type'), + 'vcodec': video.get('video_codec'), + 'width': int_or_none(video.get('width')), + 'height': int_or_none(video.get('height')), + 'filesize': get_file_size(video.get('fileSize')), } for video in video_data['renditions'] ] self._sort_formats(formats) @@ -61,7 +63,8 @@ class NYTimesIE(InfoExtractor): thumbnails = [ { 'url': 'http://www.nytimes.com/%s' % image['url'], - 'resolution': '%dx%d' % (image['width'], image['height']), + 'width': int_or_none(image.get('width')), + 'height': int_or_none(image.get('height')), } for image in video_data['images'] ] |