]>
Commit | Line | Data |
---|---|---|
1 | import re | |
2 | ||
3 | from .common import InfoExtractor | |
4 | from ..utils import ( | |
5 | determine_ext, | |
6 | float_or_none, | |
7 | HEADRequest, | |
8 | int_or_none, | |
9 | parse_duration, | |
10 | unified_strdate, | |
11 | ) | |
12 | ||
13 | ||
14 | class LA7IE(InfoExtractor): | |
15 | IE_NAME = 'la7.it' | |
16 | _VALID_URL = r'''(?x)(https?://)?(?: | |
17 | (?:www\.)?la7\.it/([^/]+)/(?:rivedila7|video)/| | |
18 | tg\.la7\.it/repliche-tgla7\?id= | |
19 | )(?P<id>.+)''' | |
20 | ||
21 | _TESTS = [{ | |
22 | # 'src' is a plain URL | |
23 | 'url': 'http://www.la7.it/crozza/video/inccool8-02-10-2015-163722', | |
24 | 'md5': '8b613ffc0c4bf9b9e377169fc19c214c', | |
25 | 'info_dict': { | |
26 | 'id': 'inccool8-02-10-2015-163722', | |
27 | 'ext': 'mp4', | |
28 | 'title': 'Inc.Cool8', | |
29 | 'description': 'Benvenuti nell\'incredibile mondo della INC. COOL. 8. dove “INC.” sta per “Incorporated” “COOL” sta per “fashion” ed Eight sta per il gesto atletico', | |
30 | 'thumbnail': 're:^https?://.*', | |
31 | 'upload_date': '20151002', | |
32 | }, | |
33 | }, { | |
34 | 'url': 'http://www.la7.it/omnibus/rivedila7/omnibus-news-02-07-2016-189077', | |
35 | 'only_matching': True, | |
36 | }] | |
37 | _HOST = 'https://awsvodpkg.iltrovatore.it' | |
38 | ||
39 | def _generate_mp4_url(self, quality, m3u8_formats): | |
40 | for f in m3u8_formats: | |
41 | if f['vcodec'] != 'none' and quality in f['url']: | |
42 | http_url = '%s%s.mp4' % (self._HOST, quality) | |
43 | ||
44 | urlh = self._request_webpage( | |
45 | HEADRequest(http_url), quality, | |
46 | note='Check filesize', fatal=False) | |
47 | if urlh: | |
48 | http_f = f.copy() | |
49 | del http_f['manifest_url'] | |
50 | http_f.update({ | |
51 | 'format_id': http_f['format_id'].replace('hls-', 'https-'), | |
52 | 'url': http_url, | |
53 | 'protocol': 'https', | |
54 | 'filesize_approx': int_or_none(urlh.headers.get('Content-Length', None)), | |
55 | }) | |
56 | return http_f | |
57 | return None | |
58 | ||
59 | def _real_extract(self, url): | |
60 | video_id = self._match_id(url) | |
61 | ||
62 | if not url.startswith('http'): | |
63 | url = '%s//%s' % (self.http_scheme(), url) | |
64 | ||
65 | webpage = self._download_webpage(url, video_id) | |
66 | video_path = self._search_regex(r'(/content/.*?).mp4', webpage, 'video_path') | |
67 | ||
68 | formats = self._extract_mpd_formats( | |
69 | f'{self._HOST}/local/dash/,{video_path}.mp4.urlset/manifest.mpd', | |
70 | video_id, mpd_id='dash', fatal=False) | |
71 | m3u8_formats = self._extract_m3u8_formats( | |
72 | f'{self._HOST}/local/hls/,{video_path}.mp4.urlset/master.m3u8', | |
73 | video_id, 'mp4', m3u8_id='hls', fatal=False) | |
74 | formats.extend(m3u8_formats) | |
75 | ||
76 | for q in filter(None, video_path.split(',')): | |
77 | http_f = self._generate_mp4_url(q, m3u8_formats) | |
78 | if http_f: | |
79 | formats.append(http_f) | |
80 | ||
81 | self._sort_formats(formats) | |
82 | ||
83 | return { | |
84 | 'id': video_id, | |
85 | 'title': self._og_search_title(webpage, default=None), | |
86 | 'description': self._og_search_description(webpage, default=None), | |
87 | 'thumbnail': self._og_search_thumbnail(webpage, default=None), | |
88 | 'formats': formats, | |
89 | 'upload_date': unified_strdate(self._search_regex(r'datetime="(.+?)"', webpage, 'upload_date', fatal=False)) | |
90 | } | |
91 | ||
92 | ||
93 | class LA7PodcastEpisodeIE(InfoExtractor): | |
94 | IE_NAME = 'la7.it:pod:episode' | |
95 | _VALID_URL = r'''(?x)(https?://)? | |
96 | (?:www\.)?la7\.it/[^/]+/podcast/([^/]+-)?(?P<id>\d+)''' | |
97 | ||
98 | _TESTS = [{ | |
99 | 'url': 'https://www.la7.it/voicetown/podcast/la-carezza-delle-memoria-di-carlo-verdone-23-03-2021-371497', | |
100 | 'md5': '7737d4d79b3c1a34b3de3e16297119ed', | |
101 | 'info_dict': { | |
102 | 'id': '371497', | |
103 | 'ext': 'mp3', | |
104 | 'title': '"La carezza delle memoria" di Carlo Verdone', | |
105 | 'description': 'md5:5abf07c3c551a687db80af3f9ceb7d52', | |
106 | 'thumbnail': 'https://www.la7.it/sites/default/files/podcast/371497.jpg', | |
107 | 'upload_date': '20210323', | |
108 | }, | |
109 | }, { | |
110 | # embed url | |
111 | 'url': 'https://www.la7.it/embed/podcast/371497', | |
112 | 'only_matching': True, | |
113 | }, { | |
114 | # date already in the title | |
115 | 'url': 'https://www.la7.it/propagandalive/podcast/lintervista-di-diego-bianchi-ad-annalisa-cuzzocrea-puntata-del-1932021-20-03-2021-371130', | |
116 | 'only_matching': True, | |
117 | }, { | |
118 | # title same as show_title | |
119 | 'url': 'https://www.la7.it/otto-e-mezzo/podcast/otto-e-mezzo-26-03-2021-372340', | |
120 | 'only_matching': True, | |
121 | }] | |
122 | ||
123 | def _extract_info(self, webpage, video_id=None, ppn=None): | |
124 | if not video_id: | |
125 | video_id = self._search_regex( | |
126 | r'data-nid=([\'"])(?P<vid>\d+)\1', | |
127 | webpage, 'video_id', group='vid') | |
128 | ||
129 | media_url = self._search_regex( | |
130 | (r'src:\s*([\'"])(?P<url>.+?mp3.+?)\1', | |
131 | r'data-podcast=([\'"])(?P<url>.+?mp3.+?)\1'), | |
132 | webpage, 'media_url', group='url') | |
133 | ext = determine_ext(media_url) | |
134 | formats = [{ | |
135 | 'url': media_url, | |
136 | 'format_id': ext, | |
137 | 'ext': ext, | |
138 | }] | |
139 | self._sort_formats(formats) | |
140 | ||
141 | title = self._html_search_regex( | |
142 | (r'<div class="title">(?P<title>.+?)</', | |
143 | r'<title>(?P<title>[^<]+)</title>', | |
144 | r'title:\s*([\'"])(?P<title>.+?)\1'), | |
145 | webpage, 'title', group='title') | |
146 | ||
147 | description = ( | |
148 | self._html_search_regex( | |
149 | (r'<div class="description">(.+?)</div>', | |
150 | r'<div class="description-mobile">(.+?)</div>', | |
151 | r'<div class="box-txt">([^<]+?)</div>', | |
152 | r'<div class="field-content"><p>(.+?)</p></div>'), | |
153 | webpage, 'description', default=None) | |
154 | or self._html_search_meta('description', webpage)) | |
155 | ||
156 | thumb = self._html_search_regex( | |
157 | (r'<div class="podcast-image"><img src="(.+?)"></div>', | |
158 | r'<div class="container-embed"[^<]+url\((.+?)\);">', | |
159 | r'<div class="field-content"><img src="(.+?)"'), | |
160 | webpage, 'thumbnail', fatal=False, default=None) | |
161 | ||
162 | duration = parse_duration(self._html_search_regex( | |
163 | r'<span class="(?:durata|duration)">([\d:]+)</span>', | |
164 | webpage, 'duration', fatal=False, default=None)) | |
165 | ||
166 | date = self._html_search_regex( | |
167 | r'class="data">\s*(?:<span>)?([\d\.]+)\s*</', | |
168 | webpage, 'date', default=None) | |
169 | ||
170 | date_alt = self._search_regex( | |
171 | r'(\d+[\./]\d+[\./]\d+)', title, 'date_alt', default=None) | |
172 | ppn = ppn or self._search_regex( | |
173 | r'ppN:\s*([\'"])(?P<ppn>.+?)\1', | |
174 | webpage, 'ppn', group='ppn', default=None) | |
175 | # if the date is not in the title | |
176 | # and title is the same as the show_title | |
177 | # add the date to the title | |
178 | if date and not date_alt and ppn and ppn.lower() == title.lower(): | |
179 | title += ' del %s' % date | |
180 | return { | |
181 | 'id': video_id, | |
182 | 'title': title, | |
183 | 'description': description, | |
184 | 'duration': float_or_none(duration), | |
185 | 'formats': formats, | |
186 | 'thumbnail': thumb, | |
187 | 'upload_date': unified_strdate(date), | |
188 | } | |
189 | ||
190 | def _real_extract(self, url): | |
191 | video_id = self._match_id(url) | |
192 | webpage = self._download_webpage(url, video_id) | |
193 | ||
194 | return self._extract_info(webpage, video_id) | |
195 | ||
196 | ||
197 | class LA7PodcastIE(LA7PodcastEpisodeIE): | |
198 | IE_NAME = 'la7.it:podcast' | |
199 | _VALID_URL = r'(https?://)?(www\.)?la7\.it/(?P<id>[^/]+)/podcast/?(?:$|[#?])' | |
200 | ||
201 | _TESTS = [{ | |
202 | 'url': 'https://www.la7.it/propagandalive/podcast', | |
203 | 'info_dict': { | |
204 | 'id': 'propagandalive', | |
205 | 'title': "Propaganda Live", | |
206 | }, | |
207 | 'playlist_count': 10, | |
208 | }] | |
209 | ||
210 | def _real_extract(self, url): | |
211 | playlist_id = self._match_id(url) | |
212 | webpage = self._download_webpage(url, playlist_id) | |
213 | ||
214 | title = ( | |
215 | self._html_search_regex( | |
216 | r'<h1.*?>(.+?)</h1>', webpage, 'title', fatal=False, default=None) | |
217 | or self._og_search_title(webpage)) | |
218 | ppn = self._search_regex( | |
219 | r'window\.ppN\s*=\s*([\'"])(?P<ppn>.+?)\1', | |
220 | webpage, 'ppn', group='ppn', default=None) | |
221 | ||
222 | entries = [] | |
223 | for episode in re.finditer( | |
224 | r'<div class="container-podcast-property">([\s\S]+?)(?:</div>\s*){3}', | |
225 | webpage): | |
226 | entries.append(self._extract_info(episode.group(1), ppn=ppn)) | |
227 | ||
228 | return self.playlist_result(entries, playlist_id, title) |