]>
jfr.im git - yt-dlp.git/blob - yt_dlp/extractor/la7.py
3 from . common
import InfoExtractor
4 from .. networking
import HEADRequest
5 from .. utils
import float_or_none
, int_or_none
, parse_duration
, unified_strdate
8 class LA7IE ( InfoExtractor
):
10 _VALID_URL
= r
'''(?x)https?://(?:
11 (?:www\.)?la7\.it/([^/]+)/(?:rivedila7|video|news)/|
12 tg\.la7\.it/repliche-tgla7\?id=
16 # single quality video
17 'url' : 'http://www.la7.it/crozza/video/inccool8-02-10-2015-163722' ,
18 'md5' : '8b613ffc0c4bf9b9e377169fc19c214c' ,
20 'id' : 'inccool8-02-10-2015-163722' ,
23 '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' ,
24 'thumbnail' : 're:^https?://.*' ,
25 'upload_date' : '20151002' ,
29 # multiple quality video
30 'url' : 'https://www.la7.it/calcio-femminile/news/il-gol-di-lindsey-thomas-fiorentina-vs-milan-serie-a-calcio-femminile-26-11-2022-461736' ,
31 'md5' : 'd2370e78f75e8d1238cb3a0db9a2eda3' ,
33 'id' : 'il-gol-di-lindsey-thomas-fiorentina-vs-milan-serie-a-calcio-femminile-26-11-2022-461736' ,
35 'title' : 'Il gol di Lindsey Thomas | Fiorentina vs Milan | Serie A Calcio Femminile' ,
36 'description' : 'Il gol di Lindsey Thomas | Fiorentina vs Milan | Serie A Calcio Femminile' ,
37 'thumbnail' : 're:^https?://.*' ,
38 'upload_date' : '20221126' ,
42 'url' : 'http://www.la7.it/omnibus/rivedila7/omnibus-news-02-07-2016-189077' ,
43 'only_matching' : True ,
45 _HOST
= 'https://awsvodpkg.iltrovatore.it'
47 def _generate_mp4_url ( self
, quality
, m3u8_formats
):
48 for f
in m3u8_formats
:
49 if f
[ 'vcodec' ] != 'none' and quality
in f
[ 'url' ]:
50 http_url
= f
' {self._HOST}{quality} .mp4'
52 urlh
= self
._ request
_ webpage
(
53 HEADRequest ( http_url
), quality
,
54 note
= 'Check filesize' , fatal
= False )
57 del http_f
[ 'manifest_url' ]
59 'format_id' : http_f
[ 'format_id' ]. replace ( 'hls-' , 'https-' ),
62 'filesize_approx' : int_or_none ( urlh
. headers
. get ( 'Content-Length' , None )),
67 def _real_extract ( self
, url
):
68 video_id
= self
._ match
_ id
( url
)
69 webpage
= self
._ download
_ webpage
( url
, video_id
)
71 if re
. search ( r
'(?i)(drmsupport\s*:\s*true)\s*' , webpage
):
72 self
. report_drm ( video_id
)
74 video_path
= self
._ search
_ regex
(
75 r
'(/content/[\w/,]+?)\.mp4(?:\.csmil)?/master\.m3u8' , webpage
, 'video_path' )
77 formats
= self
._ extract
_ mpd
_ formats
(
78 f
' {self._HOST} /local/dash/, {video_path} .mp4.urlset/manifest.mpd' ,
79 video_id
, mpd_id
= 'dash' , fatal
= False )
80 m3u8_formats
= self
._ extract
_ m
3u8_ formats
(
81 f
' {self._HOST} /local/hls/, {video_path} .mp4.urlset/master.m3u8' ,
82 video_id
, 'mp4' , m3u8_id
= 'hls' , fatal
= False )
83 formats
. extend ( m3u8_formats
)
85 for q
in filter ( None , video_path
. split ( ',' )):
86 http_f
= self
._ generate
_ mp
4_u rl
( q
, m3u8_formats
)
88 formats
. append ( http_f
)
92 'title' : self
._ og
_ search
_ title
( webpage
, default
= None ),
93 'description' : self
._ og
_ search
_ description
( webpage
, default
= None ),
94 'thumbnail' : self
._ og
_ search
_ thumbnail
( webpage
, default
= None ),
96 'upload_date' : unified_strdate ( self
._ search
_ regex
( r
'datetime="(.+?)"' , webpage
, 'upload_date' , fatal
= False ))
100 class LA7PodcastEpisodeIE ( InfoExtractor
):
101 IE_NAME
= 'la7.it:pod:episode'
102 _VALID_URL
= r
'https?://(?:www\.)?la7\.it/[^/]+/podcast/([^/]+-)?(?P<id>\d+)'
105 'url' : 'https://www.la7.it/voicetown/podcast/la-carezza-delle-memoria-di-carlo-verdone-23-03-2021-371497' ,
106 'md5' : '7737d4d79b3c1a34b3de3e16297119ed' ,
110 'title' : '"La carezza delle memoria" di Carlo Verdone' ,
111 'description' : 'md5:5abf07c3c551a687db80af3f9ceb7d52' ,
112 'thumbnail' : 'https://www.la7.it/sites/default/files/podcast/371497.jpg' ,
113 'upload_date' : '20210323' ,
117 'url' : 'https://www.la7.it/embed/podcast/371497' ,
118 'only_matching' : True ,
120 # date already in the title
121 'url' : 'https://www.la7.it/propagandalive/podcast/lintervista-di-diego-bianchi-ad-annalisa-cuzzocrea-puntata-del-1932021-20-03-2021-371130' ,
122 'only_matching' : True ,
124 # title same as show_title
125 'url' : 'https://www.la7.it/otto-e-mezzo/podcast/otto-e-mezzo-26-03-2021-372340' ,
126 'only_matching' : True ,
129 def _extract_info ( self
, webpage
, video_id
= None , ppn
= None ):
131 video_id
= self
._ search
_ regex
(
132 r
'data-nid=([\' "])(?P<vid>\d+)\1',
133 webpage, 'video_id', group='vid')
135 media_url = self._search_regex(
136 (r'src\s*:\s*([ \' " ])( ?P
< url
> \S
+ ?mp3
.+ ?
) \
1 ',
137 r' data
- podcast\s
*= \s
*([ \' "])(?P<url>\S+?mp3.+?)\1'),
138 webpage, 'media_url', group='url')
141 'format_id': 'http-mp3',
147 title = self._html_search_regex(
148 (r'<div class=" title
">(?P<title>.+?)</',
149 r'<title>(?P<title>[^<]+)</title>',
150 r'title:\s*([ \' " ])( ?P
< title
>.+ ?
) \
1 '),
151 webpage, ' title
', group=' title
')
154 self._html_search_regex(
155 (r' < div
class = "description" >(.+ ?
)</ div
> ',
156 r' < div
class = "description-mobile" >(.+ ?
)</ div
> ',
157 r' < div
class = "box-txt" >([ ^
<]+ ?
)</ div
> ',
158 r' < div
class = "field-content" >< p
>(.+ ?
)</ p
></ div
> '),
159 webpage, ' description
', default=None)
160 or self._html_search_meta(' description
', webpage))
162 thumb = self._html_search_regex(
163 (r' < div
class = "podcast-image" >< img src
= "(.+?)" ></ div
> ',
164 r' < div
class = "container-embed" [ ^
<]+ url\
((.+ ?
) \
); ">',
165 r'<div class=" field
- content
"><img src=" (.+ ?
) "'),
166 webpage, 'thumbnail', fatal=False, default=None)
168 duration = parse_duration(self._html_search_regex(
169 r'<span class=" ( ?
: durata|duration
) ">([\d:]+)</span>',
170 webpage, 'duration', fatal=False, default=None))
172 date = self._html_search_regex(
173 r'class=" data
">\s*(?:<span>)?([\d\.]+)\s*</',
174 webpage, 'date', default=None)
176 date_alt = self._search_regex(
177 r'(\d+[\./]\d+[\./]\d+)', title, 'date_alt', default=None)
178 ppn = ppn or self._search_regex(
179 r'ppN:\s*([ \' " ])( ?P
< ppn
>.+ ?
) \
1 ',
180 webpage, ' ppn
', group=' ppn
', default=None)
181 # if the date is not in the title
182 # and title is the same as the show_title
183 # add the date to the title
184 if date and not date_alt and ppn and ppn.lower() == title.lower():
185 title = f' {title}
del {date}
'
189 ' description
': description,
190 ' duration
': float_or_none(duration),
193 ' upload_date
': unified_strdate(date),
196 def _real_extract(self, url):
197 video_id = self._match_id(url)
198 webpage = self._download_webpage(url, video_id)
200 return self._extract_info(webpage, video_id)
203 class LA7PodcastIE(LA7PodcastEpisodeIE): # XXX: Do not subclass from concrete IE
204 IE_NAME = ' la7
. it
: podcast
'
205 _VALID_URL = r' https?
://( ?
: www\
.) ?la7\
. it
/( ?P
< id >[ ^
/]+)/ podcast
/ ?
( ?
: $|
[ #?])'
208 'url' : 'https://www.la7.it/propagandalive/podcast' ,
210 'id' : 'propagandalive' ,
211 'title' : 'Propaganda Live' ,
213 'playlist_mincount' : 10 ,
216 def _real_extract ( self
, url
):
217 playlist_id
= self
._ match
_ id
( url
)
218 webpage
= self
._ download
_ webpage
( url
, playlist_id
)
221 self
._ html
_ search
_ regex
(
222 r
'<h1.*?>(.+?)</h1>' , webpage
, 'title' , fatal
= False , default
= None )
223 or self
._ og
_ search
_ title
( webpage
))
224 ppn
= self
._ search
_ regex
(
225 r
'window\.ppN\s*=\s*([\' "])(?P<ppn>.+?)\1',
226 webpage, 'ppn', group='ppn', default=None)
229 for episode in re.finditer(
230 r'<div class=" container
- podcast
- property ">([\s\S]+?)(?:</div>\s*) {3} ',
232 entries.append(self._extract_info(episode.group(1), ppn=ppn))
234 return self.playlist_result(entries, playlist_id, title)