[la7.it] Fix the extractor

This commit is contained in:
Yen Chi Hsuan 2016-07-02 23:49:03 +08:00
parent 6a424391d9
commit 712b0b5b70
No known key found for this signature in database
GPG Key ID: 3FDDD575826C5C30
1 changed files with 50 additions and 36 deletions

View File

@ -1,60 +1,74 @@
# coding: utf-8
from __future__ import unicode_literals from __future__ import unicode_literals
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import ( from ..utils import (
parse_duration, determine_ext,
js_to_json,
) )
class LA7IE(InfoExtractor): class LA7IE(InfoExtractor):
IE_NAME = 'la7.tv' IE_NAME = 'la7.it'
_VALID_URL = r'''(?x) _VALID_URL = r'''(?x)(https?://)?(?:
https?://(?:www\.)?la7\.tv/ (?:www\.)?la7\.it/([^/]+)/(?:rivedila7|video)/|
(?: tg\.la7\.it/repliche-tgla7\?id=
richplayer/\?assetid=| )(?P<id>.+)'''
\?contentId=
)
(?P<id>[0-9]+)'''
_TEST = { _TESTS = [{
'url': 'http://www.la7.tv/richplayer/?assetid=50355319', # 'src' is a plain URL
'md5': 'ec7d1f0224d20ba293ab56cf2259651f', 'url': 'http://www.la7.it/crozza/video/inccool8-02-10-2015-163722',
'md5': '6054674766e7988d3e02f2148ff92180',
'info_dict': { 'info_dict': {
'id': '50355319', 'id': 'inccool8-02-10-2015-163722',
'ext': 'mp4', 'ext': 'mp4',
'title': 'IL DIVO', 'title': 'Inc.Cool8',
'description': 'Un film di Paolo Sorrentino con Toni Servillo, Anna Bonaiuto, Giulio Bosetti e Flavio Bucci', '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',
'duration': 6254, 'thumbnail': 're:^https?://.*',
}, },
'skip': 'Blocked in the US', }, {
} # 'src' is a dictionary
'url': 'http://tg.la7.it/repliche-tgla7?id=189080',
'md5': '6b0d8888d286e39870208dfeceaf456b',
'info_dict': {
'id': '189080',
'ext': 'mp4',
'title': 'TG LA7',
},
}, {
'url': 'http://www.la7.it/omnibus/rivedila7/omnibus-news-02-07-2016-189077',
'only_matching': True,
}]
def _real_extract(self, url): def _real_extract(self, url):
video_id = self._match_id(url) video_id = self._match_id(url)
xml_url = 'http://www.la7.tv/repliche/content/index.php?contentId=%s' % video_id
doc = self._download_xml(xml_url, video_id)
video_title = doc.find('title').text webpage = self._download_webpage(url, video_id)
description = doc.find('description').text
duration = parse_duration(doc.find('duration').text)
thumbnail = doc.find('img').text
view_count = int(doc.find('views').text)
prefix = doc.find('.//fqdn').text.strip().replace('auto:', 'http:') player_data = self._parse_json(
self._search_regex(r'videoLa7\(({[^;]+})\);', webpage, 'player data'),
video_id, transform_source=js_to_json)
formats = [{ source = player_data['src']
'format': vnode.find('quality').text, source_urls = source.values() if isinstance(source, dict) else [source]
'tbr': int(vnode.find('quality').text),
'url': vnode.find('fms').text.strip().replace('mp4:', prefix), formats = []
} for vnode in doc.findall('.//videos/video')] for source_url in source_urls:
ext = determine_ext(source_url)
if ext == 'm3u8':
formats.extend(self._extract_m3u8_formats(
source_url, video_id, ext='mp4',
entry_protocol='m3u8_native', m3u8_id='hls'))
else:
formats.append({
'url': source_url,
})
self._sort_formats(formats) self._sort_formats(formats)
return { return {
'id': video_id, 'id': video_id,
'title': video_title, 'title': player_data['title'],
'description': description, 'description': self._og_search_description(webpage, default=None),
'thumbnail': thumbnail, 'thumbnail': player_data.get('poster'),
'duration': duration,
'formats': formats, 'formats': formats,
'view_count': view_count,
} }