]> jfr.im git - yt-dlp.git/blob - yt_dlp/extractor/washingtonpost.py
[ie/orf:on] Improve extraction (#9677)
[yt-dlp.git] / yt_dlp / extractor / washingtonpost.py
1 import re
2
3 from .common import InfoExtractor
4
5 from ..utils import traverse_obj
6
7
8 class WashingtonPostIE(InfoExtractor):
9 IE_NAME = 'washingtonpost'
10 _VALID_URL = r'(?:washingtonpost:|https?://(?:www\.)?washingtonpost\.com/(?:video|posttv)/(?:[^/]+/)*)(?P<id>[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})'
11 _EMBED_REGEX = [r'<iframe[^>]+\bsrc=["\'](?P<url>https?://(?:www\.)?washingtonpost\.com/video/c/embed/[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})']
12 _TESTS = [{
13 'url': 'https://www.washingtonpost.com/video/c/video/480ba4ee-1ec7-11e6-82c2-a7dcb313287d',
14 'md5': '6f537e1334b714eb15f9563bd4b9cdfa',
15 'info_dict': {
16 'id': '480ba4ee-1ec7-11e6-82c2-a7dcb313287d',
17 'ext': 'mp4',
18 'title': 'Egypt finds belongings, debris from plane crash',
19 'description': 'md5:a17ceee432f215a5371388c1f680bd86',
20 'upload_date': '20160520',
21 'timestamp': 1463775187,
22 },
23 }, {
24 'url': 'https://www.washingtonpost.com/video/world/egypt-finds-belongings-debris-from-plane-crash/2016/05/20/480ba4ee-1ec7-11e6-82c2-a7dcb313287d_video.html',
25 'only_matching': True,
26 }, {
27 'url': 'https://www.washingtonpost.com/posttv/world/iraq-to-track-down-antiquities-after-islamic-state-museum-rampage/2015/02/28/7c57e916-bf86-11e4-9dfb-03366e719af8_video.html',
28 'only_matching': True,
29 }]
30
31 def _real_extract(self, url):
32 video_id = self._match_id(url)
33 return self.url_result(
34 'arcpublishing:wapo:' + video_id, 'ArcPublishing', video_id)
35
36
37 class WashingtonPostArticleIE(InfoExtractor):
38 IE_NAME = 'washingtonpost:article'
39 _VALID_URL = r'https?://(?:www\.)?washingtonpost\.com/(?:[^/]+/)*(?P<id>[^/?#]+)'
40 _TESTS = [{
41 'url': 'http://www.washingtonpost.com/sf/national/2014/03/22/sinkhole-of-bureaucracy/',
42 'info_dict': {
43 'id': 'sinkhole-of-bureaucracy',
44 'title': 'Sinkhole of bureaucracy',
45 },
46 'playlist': [{
47 'md5': '7ccf53ea8cbb77de5f570242b3b21a59',
48 'info_dict': {
49 'id': 'fc433c38-b146-11e3-b8b3-44b1d1cd4c1f',
50 'ext': 'mp4',
51 'title': 'Breaking Points: The Paper Mine',
52 'duration': 1290,
53 'description': 'Overly complicated paper pushing is nothing new to government bureaucracy. But the way federal retirement applications are filed may be the most outdated. David Fahrenthold explains.',
54 'timestamp': 1395440416,
55 'upload_date': '20140321',
56 'thumbnail': r're:https://[^\.]+.cloudfront\.net/PAPERMINESplash\.jpg',
57 },
58 }, {
59 'md5': '7ccf53ea8cbb77de5f570242b3b21a59',
60 'info_dict': {
61 'id': '41255e28-b14a-11e3-b8b3-44b1d1cd4c1f',
62 'ext': 'mp4',
63 'title': 'The town bureaucracy sustains',
64 'description': 'Underneath the friendly town of Boyers is a sea of government paperwork. In a disused limestone mine, hundreds of locals now track, file and process retirement applications for the federal government. We set out to find out what it\'s like to do paperwork 230 feet underground.',
65 'duration': 2220,
66 'timestamp': 1395441819,
67 'upload_date': '20140321',
68 'thumbnail': r're:https://[^\.]+.cloudfront\.net/BoyersSplash\.jpeg',
69 },
70 }],
71 }, {
72 'url': 'http://www.washingtonpost.com/blogs/wonkblog/wp/2014/12/31/one-airline-figured-out-how-to-make-sure-its-airplanes-never-disappear/',
73 'info_dict': {
74 'id': 'one-airline-figured-out-how-to-make-sure-its-airplanes-never-disappear',
75 'title': 'One airline figured out how to make sure its airplanes never disappear',
76 },
77 'playlist': [{
78 'md5': 'a7c1b5634ba5e57a6a82cdffa5b1e0d0',
79 'info_dict': {
80 'id': '0e4bb54c-9065-11e4-a66f-0ca5037a597d',
81 'ext': 'mp4',
82 'description': 'Washington Post transportation reporter Ashley Halsey III explains why a plane\'s black box needs to be recovered from a crash site instead of having its information streamed in real time throughout the flight.',
83 'upload_date': '20141230',
84 'timestamp': 1419972442,
85 'title': 'Why black boxes don’t transmit data in real time',
86 }
87 }],
88 'skip': 'Doesnt have a video anymore',
89 }, {
90 'url': 'https://www.washingtonpost.com/nation/2021/08/05/dixie-river-fire-california-climate/',
91 'only_matching': True,
92 }]
93
94 @classmethod
95 def suitable(cls, url):
96 return False if WashingtonPostIE.suitable(url) else super(WashingtonPostArticleIE, cls).suitable(url)
97
98 def _real_extract(self, url):
99 page_id = self._match_id(url)
100 webpage = self._download_webpage(url, page_id)
101
102 title = self._og_search_title(webpage)
103
104 uuids = re.findall(r'''(?x)
105 (?:
106 <div\s+class="posttv-video-embed[^>]*?data-uuid=|
107 data-video-uuid=
108 )"([^"]+)"''', webpage)
109
110 if not uuids:
111 json_data = self._search_nextjs_data(webpage, page_id)
112 for content_element in traverse_obj(json_data, ('props', 'pageProps', 'globalContent', 'content_elements')):
113 if content_element.get('type') == 'video':
114 uuids.append(content_element.get('_id'))
115
116 entries = [self.url_result('washingtonpost:%s' % uuid, 'WashingtonPost', uuid) for uuid in uuids]
117
118 return {
119 '_type': 'playlist',
120 'entries': entries,
121 'id': page_id,
122 'title': title,
123 }