[extractor/la7] Improve extractor (#5538)

Authored by: nixxo
Closes #5360
This commit is contained in:
nixxo 2022-12-08 17:52:19 +01:00 committed by GitHub
parent 839e2a62ae
commit 72f96c5566
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23

View file

@ -2,7 +2,6 @@
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import ( from ..utils import (
determine_ext,
float_or_none, float_or_none,
HEADRequest, HEADRequest,
int_or_none, int_or_none,
@ -13,13 +12,13 @@
class LA7IE(InfoExtractor): class LA7IE(InfoExtractor):
IE_NAME = 'la7.it' IE_NAME = 'la7.it'
_VALID_URL = r'''(?x)(https?://)?(?: _VALID_URL = r'''(?x)https?://(?:
(?:www\.)?la7\.it/([^/]+)/(?:rivedila7|video)/| (?:www\.)?la7\.it/([^/]+)/(?:rivedila7|video|news)/|
tg\.la7\.it/repliche-tgla7\?id= tg\.la7\.it/repliche-tgla7\?id=
)(?P<id>.+)''' )(?P<id>.+)'''
_TESTS = [{ _TESTS = [{
# 'src' is a plain URL # single quality video
'url': 'http://www.la7.it/crozza/video/inccool8-02-10-2015-163722', 'url': 'http://www.la7.it/crozza/video/inccool8-02-10-2015-163722',
'md5': '8b613ffc0c4bf9b9e377169fc19c214c', 'md5': '8b613ffc0c4bf9b9e377169fc19c214c',
'info_dict': { 'info_dict': {
@ -29,6 +28,20 @@ class LA7IE(InfoExtractor):
'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', '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',
'thumbnail': 're:^https?://.*', 'thumbnail': 're:^https?://.*',
'upload_date': '20151002', 'upload_date': '20151002',
'formats': 'count:4',
},
}, {
# multiple quality video
'url': 'https://www.la7.it/calcio-femminile/news/il-gol-di-lindsey-thomas-fiorentina-vs-milan-serie-a-calcio-femminile-26-11-2022-461736',
'md5': 'd2370e78f75e8d1238cb3a0db9a2eda3',
'info_dict': {
'id': 'il-gol-di-lindsey-thomas-fiorentina-vs-milan-serie-a-calcio-femminile-26-11-2022-461736',
'ext': 'mp4',
'title': 'Il gol di Lindsey Thomas | Fiorentina vs Milan | Serie A Calcio Femminile',
'description': 'Il gol di Lindsey Thomas | Fiorentina vs Milan | Serie A Calcio Femminile',
'thumbnail': 're:^https?://.*',
'upload_date': '20221126',
'formats': 'count:8',
}, },
}, { }, {
'url': 'http://www.la7.it/omnibus/rivedila7/omnibus-news-02-07-2016-189077', 'url': 'http://www.la7.it/omnibus/rivedila7/omnibus-news-02-07-2016-189077',
@ -39,7 +52,7 @@ class LA7IE(InfoExtractor):
def _generate_mp4_url(self, quality, m3u8_formats): def _generate_mp4_url(self, quality, m3u8_formats):
for f in m3u8_formats: for f in m3u8_formats:
if f['vcodec'] != 'none' and quality in f['url']: if f['vcodec'] != 'none' and quality in f['url']:
http_url = '%s%s.mp4' % (self._HOST, quality) http_url = f'{self._HOST}{quality}.mp4'
urlh = self._request_webpage( urlh = self._request_webpage(
HEADRequest(http_url), quality, HEADRequest(http_url), quality,
@ -58,12 +71,13 @@ def _generate_mp4_url(self, quality, m3u8_formats):
def _real_extract(self, url): def _real_extract(self, url):
video_id = self._match_id(url) video_id = self._match_id(url)
if not url.startswith('http'):
url = '%s//%s' % (self.http_scheme(), url)
webpage = self._download_webpage(url, video_id) webpage = self._download_webpage(url, video_id)
video_path = self._search_regex(r'(/content/.*?).mp4', webpage, 'video_path')
if re.search(r'(?i)(drmsupport\s*:\s*true)\s*', webpage):
self.report_drm(video_id)
video_path = self._search_regex(
r'(/content/[\w/,]+?)\.mp4(?:\.csmil)?/master\.m3u8', webpage, 'video_path')
formats = self._extract_mpd_formats( formats = self._extract_mpd_formats(
f'{self._HOST}/local/dash/,{video_path}.mp4.urlset/manifest.mpd', f'{self._HOST}/local/dash/,{video_path}.mp4.urlset/manifest.mpd',
@ -90,8 +104,7 @@ def _real_extract(self, url):
class LA7PodcastEpisodeIE(InfoExtractor): class LA7PodcastEpisodeIE(InfoExtractor):
IE_NAME = 'la7.it:pod:episode' IE_NAME = 'la7.it:pod:episode'
_VALID_URL = r'''(?x)(https?://)? _VALID_URL = r'https?://(?:www\.)?la7\.it/[^/]+/podcast/([^/]+-)?(?P<id>\d+)'
(?:www\.)?la7\.it/[^/]+/podcast/([^/]+-)?(?P<id>\d+)'''
_TESTS = [{ _TESTS = [{
'url': 'https://www.la7.it/voicetown/podcast/la-carezza-delle-memoria-di-carlo-verdone-23-03-2021-371497', 'url': 'https://www.la7.it/voicetown/podcast/la-carezza-delle-memoria-di-carlo-verdone-23-03-2021-371497',
@ -125,14 +138,15 @@ def _extract_info(self, webpage, video_id=None, ppn=None):
webpage, 'video_id', group='vid') webpage, 'video_id', group='vid')
media_url = self._search_regex( media_url = self._search_regex(
(r'src:\s*([\'"])(?P<url>.+?mp3.+?)\1', (r'src\s*:\s*([\'"])(?P<url>\S+?mp3.+?)\1',
r'data-podcast=([\'"])(?P<url>.+?mp3.+?)\1'), r'data-podcast\s*=\s*([\'"])(?P<url>\S+?mp3.+?)\1'),
webpage, 'media_url', group='url') webpage, 'media_url', group='url')
ext = determine_ext(media_url)
formats = [{ formats = [{
'url': media_url, 'url': media_url,
'format_id': ext, 'format_id': 'http-mp3',
'ext': ext, 'ext': 'mp3',
'acodec': 'mp3',
'vcodec': 'none',
}] }]
title = self._html_search_regex( title = self._html_search_regex(
@ -173,7 +187,7 @@ def _extract_info(self, webpage, video_id=None, ppn=None):
# and title is the same as the show_title # and title is the same as the show_title
# add the date to the title # add the date to the title
if date and not date_alt and ppn and ppn.lower() == title.lower(): if date and not date_alt and ppn and ppn.lower() == title.lower():
title += ' del %s' % date title = f'{title} del {date}'
return { return {
'id': video_id, 'id': video_id,
'title': title, 'title': title,
@ -193,7 +207,7 @@ def _real_extract(self, url):
class LA7PodcastIE(LA7PodcastEpisodeIE): # XXX: Do not subclass from concrete IE class LA7PodcastIE(LA7PodcastEpisodeIE): # XXX: Do not subclass from concrete IE
IE_NAME = 'la7.it:podcast' IE_NAME = 'la7.it:podcast'
_VALID_URL = r'(https?://)?(www\.)?la7\.it/(?P<id>[^/]+)/podcast/?(?:$|[#?])' _VALID_URL = r'https?://(?:www\.)?la7\.it/(?P<id>[^/]+)/podcast/?(?:$|[#?])'
_TESTS = [{ _TESTS = [{
'url': 'https://www.la7.it/propagandalive/podcast', 'url': 'https://www.la7.it/propagandalive/podcast',
@ -201,7 +215,7 @@ class LA7PodcastIE(LA7PodcastEpisodeIE): # XXX: Do not subclass from concrete I
'id': 'propagandalive', 'id': 'propagandalive',
'title': "Propaganda Live", 'title': "Propaganda Live",
}, },
'playlist_count': 10, 'playlist_count_min': 10,
}] }]
def _real_extract(self, url): def _real_extract(self, url):