R-yan/l1ving_youtube-dl
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

[nytimes] cleanup, add a fallback from json parsing

Browse Source
This commit is contained in:
John Hawkinson 2016-10-14 23:28:59 -04:00
parent 7096a99ce7
commit 2117b36d09
1 changed files with 14 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

19
youtube_dl/extractor/nytimes.py
View File

@ -101,13 +101,10 @@ class NYTimesBaseIE(InfoExtractor):
def _extract_podcast_from_json(self, json, page_id, webpage): def _extract_podcast_from_json(self, json, page_id, webpage):
audio_data = self._parse_json(json, page_id, transform_source=js_to_json)['data'] audio_data = self._parse_json(json, page_id, transform_source=js_to_json)['data']
print audio_data
description = audio_data['track']['description'] description = audio_data['track']['description']
if not len(description): if not len(description):
description = self._html_search_meta(['og:description', 'twitter:description'], webpage) description = self._html_search_meta(['og:description', 'twitter:description'], webpage)
episode_title = audio_data['track']['title'].strip(u"‘’") # strip curlyquotes episode_title = audio_data['track']['title'].strip(u"‘’") # strip curlyquotes
episode_number = None episode_number = None
episode = audio_data['podcast']['episode'].split() episode = audio_data['podcast']['episode'].split()
@ -117,7 +114,6 @@ class NYTimesBaseIE(InfoExtractor):
else: else:
video_id = page_id video_id = page_id
podcast_title = audio_data['podcast']['title'] podcast_title = audio_data['podcast']['title']
title = None title = None
if podcast_title: if podcast_title:
@ -128,6 +124,7 @@ class NYTimesBaseIE(InfoExtractor):
info_dict = { info_dict = {
'id': video_id, 'id': video_id,
'title': title, 'title': title,
'creator': audio_data['track'].get('credit'),
'series': audio_data['podcast']['title'], 'series': audio_data['podcast']['title'],
'episode': episode_title, 'episode': episode_title,
'episode_number': episode_number, 'episode_number': episode_number,
@ -139,7 +136,6 @@ class NYTimesBaseIE(InfoExtractor):
return info_dict return info_dict
class NYTimesIE(NYTimesBaseIE): class NYTimesIE(NYTimesBaseIE):
_VALID_URL = r'https?://(?:(?:www\.)?nytimes\.com/video/(?:[^/]+/)+?|graphics8\.nytimes\.com/bcvideo/\d+(?:\.\d+)?/iframe/embed\.html\?videoId=)(?P<id>\d+)' _VALID_URL = r'https?://(?:(?:www\.)?nytimes\.com/video/(?:[^/]+/)+?|graphics8\.nytimes\.com/bcvideo/\d+(?:\.\d+)?/iframe/embed\.html\?videoId=)(?P<id>\d+)'
@ -213,6 +209,17 @@ class NYTimesArticleIE(NYTimesBaseIE):
if video_id is not None: if video_id is not None:
return self._extract_video_from_id(video_id) return self._extract_video_from_id(video_id)
data_json = self._html_search_regex(r'NYTD.FlexTypes.push\(({[^)]*)\)', webpage, 'json data'); data_json = self._html_search_regex(r'NYTD.FlexTypes.push\(({[^)]*)\)', webpage, 'json data', None, False);
if data_json is not None: if data_json is not None:
return self._extract_podcast_from_json(data_json, page_id, webpage) return self._extract_podcast_from_json(data_json, page_id, webpage)
# Fallback case
# "source":"https:\/\/rss.art19.com\/episodes\/0e2bd0b3-10ef-42c4-9494-0e3d21d2b82a.mp3","
url=self._html_search_regex(r'"source":"(https?:[^"]+)"', webpage, 'mp3 url')
url = url.replace('\\/','/')
if url is not None:
return {
'id': page_id,
'title': self._og_search_title(webpage),
'url': url
}