[vice:show] Add extractor (Closes #8847)

This commit is contained in:
Sergey M․ 2016-03-13 17:22:23 +06:00
parent 7f4173ae7c
commit 0a477f8731
2 changed files with 61 additions and 20 deletions

View File

@ -836,7 +836,10 @@ from .vgtv import (
VGTVIE, VGTVIE,
) )
from .vh1 import VH1IE from .vh1 import VH1IE
from .vice import ViceIE from .vice import (
ViceIE,
ViceShowIE,
)
from .viddler import ViddlerIE from .viddler import ViddlerIE
from .videodetective import VideoDetectiveIE from .videodetective import VideoDetectiveIE
from .videofyme import VideofyMeIE from .videofyme import VideofyMeIE

View File

@ -1,16 +1,17 @@
from __future__ import unicode_literals from __future__ import unicode_literals
import re
from .common import InfoExtractor from .common import InfoExtractor
from .ooyala import OoyalaIE from .ooyala import OoyalaIE
from ..utils import ExtractorError from ..utils import ExtractorError
class ViceIE(InfoExtractor): class ViceIE(InfoExtractor):
_VALID_URL = r'https?://(?:.+?\.)?vice\.com/(?:[^/]+/)+(?P<id>.+)' _VALID_URL = r'https?://(?:.+?\.)?vice\.com/(?:[^/]+/)?videos?/(?P<id>[^/?#&]+)'
_TESTS = [ _TESTS = [{
{ 'url': 'http://www.vice.com/video/cowboy-capitalists-part-1',
'url': 'http://www.vice.com/Fringes/cowboy-capitalists-part-1',
'info_dict': { 'info_dict': {
'id': '43cW1mYzpia9IlestBjVpd23Yu3afAfp', 'id': '43cW1mYzpia9IlestBjVpd23Yu3afAfp',
'ext': 'mp4', 'ext': 'mp4',
@ -24,8 +25,13 @@ class ViceIE(InfoExtractor):
}, { }, {
'url': 'https://news.vice.com/video/experimenting-on-animals-inside-the-monkey-lab', 'url': 'https://news.vice.com/video/experimenting-on-animals-inside-the-monkey-lab',
'only_matching': True, 'only_matching': True,
} }, {
] 'url': 'http://www.vice.com/ru/video/big-night-out-ibiza-clive-martin-229',
'only_matching': True,
}, {
'url': 'https://munchies.vice.com/en/videos/watch-the-trailer-for-our-new-series-the-pizza-show',
'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)
@ -38,3 +44,35 @@ class ViceIE(InfoExtractor):
except ExtractorError: except ExtractorError:
raise ExtractorError('The page doesn\'t contain a video', expected=True) raise ExtractorError('The page doesn\'t contain a video', expected=True)
return self.url_result(ooyala_url, ie='Ooyala') return self.url_result(ooyala_url, ie='Ooyala')
class ViceShowIE(InfoExtractor):
_VALID_URL = r'https?://(?:.+?\.)?vice\.com/(?:[^/]+/)?show/(?P<id>[^/?#&]+)'
_TEST = {
'url': 'https://munchies.vice.com/en/show/fuck-thats-delicious-2',
'info_dict': {
'id': 'fuck-thats-delicious-2',
'title': "Fuck, That's Delicious",
'description': 'Follow the culinary adventures of rapper Action Bronson during his ongoing world tour.',
},
'playlist_count': 17,
}
def _real_extract(self, url):
show_id = self._match_id(url)
webpage = self._download_webpage(url, show_id)
entries = [
self.url_result(video_url, ViceIE.ie_key())
for video_url, _ in re.findall(
r'<h2[^>]+class="article-title"[^>]+data-id="\d+"[^>]*>\s*<a[^>]+href="(%s.*?)"'
% ViceIE._VALID_URL, webpage)]
title = self._search_regex(
r'<title>(.+?)</title>', webpage, 'title', default=None)
if title:
title = re.sub(r'(.+)\s*\|\s*.+$', r'\1', title).strip()
description = self._html_search_meta('description', webpage, 'description')
return self.playlist_result(entries, show_id, title, description)