]> Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/seznamzpravy.py
Fix extraction from youtube.
[youtubedl] / youtube_dl / extractor / seznamzpravy.py
1 # coding: utf-8
2 from __future__ import unicode_literals
3
4 import re
5
6 from .common import InfoExtractor
7 from ..compat import (
8 compat_parse_qs,
9 compat_str,
10 compat_urllib_parse_urlparse,
11 )
12 from ..utils import (
13 urljoin,
14 int_or_none,
15 parse_codecs,
16 try_get,
17 )
18
19
20 def _raw_id(src_url):
21 return compat_urllib_parse_urlparse(src_url).path.split('/')[-1]
22
23
24 class SeznamZpravyIE(InfoExtractor):
25 _VALID_URL = r'https?://(?:www\.)?seznamzpravy\.cz/iframe/player\?.*\bsrc='
26 _TESTS = [{
27 'url': 'https://www.seznamzpravy.cz/iframe/player?duration=241&serviceSlug=zpravy&src=https%3A%2F%2Fv39-a.sdn.szn.cz%2Fv_39%2Fvmd%2F5999c902ea707c67d8e267a9%3Ffl%3Dmdk%2C432f65a0%7C&itemType=video&autoPlay=false&title=Sv%C4%9Bt%20bez%20obalu%3A%20%C4%8Ce%C5%A1t%C3%AD%20voj%C3%A1ci%20na%20mis%C3%ADch%20(kr%C3%A1tk%C3%A1%20verze)&series=Sv%C4%9Bt%20bez%20obalu&serviceName=Seznam%20Zpr%C3%A1vy&poster=%2F%2Fd39-a.sdn.szn.cz%2Fd_39%2Fc_img_F_I%2FR5puJ.jpeg%3Ffl%3Dcro%2C0%2C0%2C1920%2C1080%7Cres%2C1200%2C%2C1%7Cjpg%2C80%2C%2C1&width=1920&height=1080&cutFrom=0&cutTo=0&splVersion=VOD&contentId=170889&contextId=35990&showAdvert=true&collocation=&autoplayPossible=true&embed=&isVideoTooShortForPreroll=false&isVideoTooLongForPostroll=true&videoCommentOpKey=&videoCommentId=&version=4.0.76&dotService=zpravy&gemiusPrismIdentifier=bVc1ZIb_Qax4W2v5xOPGpMeCP31kFfrTzj0SqPTLh_b.Z7&zoneIdPreroll=seznam.pack.videospot&skipOffsetPreroll=5&sectionPrefixPreroll=%2Fzpravy',
28 'info_dict': {
29 'id': '170889',
30 'ext': 'mp4',
31 'title': 'Svět bez obalu: Čeští vojáci na misích (krátká verze)',
32 'thumbnail': r're:^https?://.*\.jpe?g',
33 'duration': 241,
34 'series': 'Svět bez obalu',
35 },
36 'params': {
37 'skip_download': True,
38 },
39 }, {
40 # with Location key
41 'url': 'https://www.seznamzpravy.cz/iframe/player?duration=null&serviceSlug=zpravy&src=https%3A%2F%2Flive-a.sdn.szn.cz%2Fv_39%2F59e468fe454f8472a96af9fa%3Ffl%3Dmdk%2C5c1e2840%7C&itemType=livevod&autoPlay=false&title=P%C5%99edseda%20KDU-%C4%8CSL%20Pavel%20B%C4%9Blobr%C3%A1dek%20ve%20volebn%C3%AD%20V%C3%BDzv%C4%9B%20Seznamu&series=V%C3%BDzva&serviceName=Seznam%20Zpr%C3%A1vy&poster=%2F%2Fd39-a.sdn.szn.cz%2Fd_39%2Fc_img_G_J%2FjTBCs.jpeg%3Ffl%3Dcro%2C0%2C0%2C1280%2C720%7Cres%2C1200%2C%2C1%7Cjpg%2C80%2C%2C1&width=16&height=9&cutFrom=0&cutTo=0&splVersion=VOD&contentId=185688&contextId=38489&showAdvert=true&collocation=&hideFullScreen=false&hideSubtitles=false&embed=&isVideoTooShortForPreroll=false&isVideoTooShortForPreroll2=false&isVideoTooLongForPostroll=false&fakePostrollZoneID=seznam.clanky.zpravy.preroll&fakePrerollZoneID=seznam.clanky.zpravy.preroll&videoCommentId=&trim=default_16x9&noPrerollVideoLength=30&noPreroll2VideoLength=undefined&noMidrollVideoLength=0&noPostrollVideoLength=999999&autoplayPossible=true&version=5.0.41&dotService=zpravy&gemiusPrismIdentifier=zD3g7byfW5ekpXmxTVLaq5Srjw5i4hsYo0HY1aBwIe..27&zoneIdPreroll=seznam.pack.videospot&skipOffsetPreroll=5&sectionPrefixPreroll=%2Fzpravy%2Fvyzva&zoneIdPostroll=seznam.pack.videospot&skipOffsetPostroll=5&sectionPrefixPostroll=%2Fzpravy%2Fvyzva&regression=false',
42 'info_dict': {
43 'id': '185688',
44 'ext': 'mp4',
45 'title': 'Předseda KDU-ČSL Pavel Bělobrádek ve volební Výzvě Seznamu',
46 'thumbnail': r're:^https?://.*\.jpe?g',
47 'series': 'Výzva',
48 },
49 'params': {
50 'skip_download': True,
51 },
52 }]
53
54 @staticmethod
55 def _extract_urls(webpage):
56 return [
57 mobj.group('url') for mobj in re.finditer(
58 r'<iframe\b[^>]+\bsrc=(["\'])(?P<url>(?:https?:)?//(?:www\.)?seznamzpravy\.cz/iframe/player\?.*?)\1',
59 webpage)]
60
61 def _extract_sdn_formats(self, sdn_url, video_id):
62 sdn_data = self._download_json(sdn_url, video_id)
63
64 if sdn_data.get('Location'):
65 sdn_url = sdn_data['Location']
66 sdn_data = self._download_json(sdn_url, video_id)
67
68 formats = []
69 mp4_formats = try_get(sdn_data, lambda x: x['data']['mp4'], dict) or {}
70 for format_id, format_data in mp4_formats.items():
71 relative_url = format_data.get('url')
72 if not relative_url:
73 continue
74
75 try:
76 width, height = format_data.get('resolution')
77 except (TypeError, ValueError):
78 width, height = None, None
79
80 f = {
81 'url': urljoin(sdn_url, relative_url),
82 'format_id': 'http-%s' % format_id,
83 'tbr': int_or_none(format_data.get('bandwidth'), scale=1000),
84 'width': int_or_none(width),
85 'height': int_or_none(height),
86 }
87 f.update(parse_codecs(format_data.get('codec')))
88 formats.append(f)
89
90 pls = sdn_data.get('pls', {})
91
92 def get_url(format_id):
93 return try_get(pls, lambda x: x[format_id]['url'], compat_str)
94
95 dash_rel_url = get_url('dash')
96 if dash_rel_url:
97 formats.extend(self._extract_mpd_formats(
98 urljoin(sdn_url, dash_rel_url), video_id, mpd_id='dash',
99 fatal=False))
100
101 hls_rel_url = get_url('hls')
102 if hls_rel_url:
103 formats.extend(self._extract_m3u8_formats(
104 urljoin(sdn_url, hls_rel_url), video_id, ext='mp4',
105 m3u8_id='hls', fatal=False))
106
107 self._sort_formats(formats)
108 return formats
109
110 def _real_extract(self, url):
111 params = compat_parse_qs(compat_urllib_parse_urlparse(url).query)
112
113 src = params['src'][0]
114 title = params['title'][0]
115 video_id = params.get('contentId', [_raw_id(src)])[0]
116 formats = self._extract_sdn_formats(src + 'spl2,2,VOD', video_id)
117
118 duration = int_or_none(params.get('duration', [None])[0])
119 series = params.get('series', [None])[0]
120 thumbnail = params.get('poster', [None])[0]
121
122 return {
123 'id': video_id,
124 'title': title,
125 'thumbnail': thumbnail,
126 'duration': duration,
127 'series': series,
128 'formats': formats,
129 }
130
131
132 class SeznamZpravyArticleIE(InfoExtractor):
133 _VALID_URL = r'https?://(?:www\.)?(?:seznam\.cz/zpravy|seznamzpravy\.cz)/clanek/(?:[^/?#&]+)-(?P<id>\d+)'
134 _API_URL = 'https://apizpravy.seznam.cz/'
135
136 _TESTS = [{
137 # two videos on one page, with SDN URL
138 'url': 'https://www.seznamzpravy.cz/clanek/jejich-svet-na-nas-utoci-je-lepsi-branit-se-na-jejich-pisecku-rika-reziser-a-major-v-zaloze-marhoul-35990',
139 'info_dict': {
140 'id': '35990',
141 'title': 'md5:6011c877a36905f28f271fcd8dcdb0f2',
142 'description': 'md5:933f7b06fa337a814ba199d3596d27ba',
143 },
144 'playlist_count': 2,
145 }, {
146 # video with live stream URL
147 'url': 'https://www.seznam.cz/zpravy/clanek/znovu-do-vlady-s-ano-pavel-belobradek-ve-volebnim-specialu-seznamu-38489',
148 'info_dict': {
149 'id': '38489',
150 'title': 'md5:8fa1afdc36fd378cf0eba2b74c5aca60',
151 'description': 'md5:428e7926a1a81986ec7eb23078004fb4',
152 },
153 'playlist_count': 1,
154 }]
155
156 def _real_extract(self, url):
157 article_id = self._match_id(url)
158
159 webpage = self._download_webpage(url, article_id)
160
161 info = self._search_json_ld(webpage, article_id, default={})
162
163 title = info.get('title') or self._og_search_title(webpage, fatal=False)
164 description = info.get('description') or self._og_search_description(webpage)
165
166 return self.playlist_result([
167 self.url_result(entry_url, ie=SeznamZpravyIE.ie_key())
168 for entry_url in SeznamZpravyIE._extract_urls(webpage)],
169 article_id, title, description)