[vice] Fix extraction for non en_us videos (closes #12967)

This commit is contained in:
Yen Chi Hsuan 2017-05-05 20:01:02 +08:00
parent 50ad078b7b
commit cc7bda4fff
No known key found for this signature in database
GPG key ID: 7F902A182457CA23
3 changed files with 37 additions and 9 deletions

View file

@ -1,6 +1,7 @@
version <unreleased> version <unreleased>
Extractors Extractors
* [vice] Fix extraction for non en_us videos (#12967)
* [gdcvault] Fix extraction for some videos (#12733) * [gdcvault] Fix extraction for some videos (#12733)
+ [cda] Support birthday verification (#12789) + [cda] Support birthday verification (#12789)
* [leeco] Fix extraction (#12974) * [leeco] Fix extraction (#12974)

View file

@ -20,7 +20,7 @@ from ..utils import (
class ViceBaseIE(AdobePassIE): class ViceBaseIE(AdobePassIE):
def _extract_preplay_video(self, url, webpage): def _extract_preplay_video(self, url, locale, webpage):
watch_hub_data = extract_attributes(self._search_regex( watch_hub_data = extract_attributes(self._search_regex(
r'(?s)(<watch-hub\s*.+?</watch-hub>)', webpage, 'watch hub')) r'(?s)(<watch-hub\s*.+?</watch-hub>)', webpage, 'watch hub'))
video_id = watch_hub_data['vms-id'] video_id = watch_hub_data['vms-id']
@ -45,7 +45,7 @@ class ViceBaseIE(AdobePassIE):
try: try:
host = 'www.viceland' if is_locked else self._PREPLAY_HOST host = 'www.viceland' if is_locked else self._PREPLAY_HOST
preplay = self._download_json('https://%s.com/en_us/preplay/%s' % (host, video_id), video_id, query=query) preplay = self._download_json('https://%s.com/%s/preplay/%s' % (host, locale, video_id), video_id, query=query)
except ExtractorError as e: except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 400: if isinstance(e.cause, compat_HTTPError) and e.cause.code == 400:
error = json.loads(e.cause.read().decode()) error = json.loads(e.cause.read().decode())
@ -88,7 +88,7 @@ class ViceBaseIE(AdobePassIE):
class ViceIE(ViceBaseIE): class ViceIE(ViceBaseIE):
_VALID_URL = r'https?://(?:.+?\.)?vice\.com/(?:[^/]+/)?videos?/(?P<id>[^/?#&]+)' _VALID_URL = r'https?://(?:.+?\.)?vice\.com/(?P<locale>[^/]+/)(?:[^/]+/)?videos?/(?P<id>[^/?#&]+)'
_TESTS = [{ _TESTS = [{
'url': 'http://www.vice.com/video/cowboy-capitalists-part-1', 'url': 'http://www.vice.com/video/cowboy-capitalists-part-1',
@ -115,20 +115,39 @@ class ViceIE(ViceBaseIE):
'add_ie': ['Youtube'], 'add_ie': ['Youtube'],
}, { }, {
'url': 'https://video.vice.com/en_us/video/the-signal-from-tolva/5816510690b70e6c5fd39a56', 'url': 'https://video.vice.com/en_us/video/the-signal-from-tolva/5816510690b70e6c5fd39a56',
'md5': '',
'info_dict': { 'info_dict': {
'id': '5816510690b70e6c5fd39a56', 'id': '5816510690b70e6c5fd39a56',
'ext': 'mp4', 'ext': 'mp4',
'uploader': 'Waypoint', 'uploader': 'Waypoint',
'title': 'The Signal From Tölva', 'title': 'The Signal From Tölva',
'description': 'md5:3927e3c79f9e8094606a2b3c5b5e55d5',
'uploader_id': '57f7d621e05ca860fa9ccaf9', 'uploader_id': '57f7d621e05ca860fa9ccaf9',
'timestamp': 1477941983938, 'timestamp': 1477941983,
'upload_date': '20161031',
}, },
'params': { 'params': {
# m3u8 download # m3u8 download
'skip_download': True, 'skip_download': True,
}, },
'add_ie': ['UplynkPreplay'], 'add_ie': ['UplynkPreplay'],
}, {
'url': 'https://video.vice.com/alps/video/ulfs-wien-beruchtigste-grafitti-crew-part-1/581b12b60a0e1f4c0fb6ea2f',
'info_dict': {
'id': '581b12b60a0e1f4c0fb6ea2f',
'ext': 'mp4',
'title': 'ULFs - Wien berüchtigste Grafitti Crew - Part 1',
'description': '<p>Zwischen Hinterzimmer-Tattoos und U-Bahnschächten erzählen uns die Ulfs, wie es ist, "süchtig nach Sachbeschädigung" zu sein.</p>',
'uploader': 'VICE',
'uploader_id': '57a204088cb727dec794c67b',
'timestamp': 1485368119,
'upload_date': '20170125',
'age_limit': 14,
},
'params': {
# AES-encrypted m3u8
'skip_download': True,
},
'add_ie': ['UplynkPreplay'],
}, { }, {
'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,
@ -142,6 +161,9 @@ class ViceIE(ViceBaseIE):
_PREPLAY_HOST = 'video.vice' _PREPLAY_HOST = 'video.vice'
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
locale = mobj.group('locale')
video_id = self._match_id(url) video_id = self._match_id(url)
webpage, urlh = self._download_webpage_handle(url, video_id) webpage, urlh = self._download_webpage_handle(url, video_id)
embed_code = self._search_regex( embed_code = self._search_regex(
@ -153,7 +175,7 @@ class ViceIE(ViceBaseIE):
r'data-youtube-id="([^"]+)"', webpage, 'youtube id', default=None) r'data-youtube-id="([^"]+)"', webpage, 'youtube id', default=None)
if youtube_id: if youtube_id:
return self.url_result(youtube_id, 'Youtube') return self.url_result(youtube_id, 'Youtube')
return self._extract_preplay_video(urlh.geturl(), webpage) return self._extract_preplay_video(urlh.geturl(), locale, webpage)
class ViceShowIE(InfoExtractor): class ViceShowIE(InfoExtractor):

View file

@ -1,11 +1,13 @@
# coding: utf-8 # coding: utf-8
from __future__ import unicode_literals from __future__ import unicode_literals
import re
from .vice import ViceBaseIE from .vice import ViceBaseIE
class VicelandIE(ViceBaseIE): class VicelandIE(ViceBaseIE):
_VALID_URL = r'https?://(?:www\.)?viceland\.com/[^/]+/video/[^/]+/(?P<id>[a-f0-9]+)' _VALID_URL = r'https?://(?:www\.)?viceland\.com/(?P<locale>[^/]+)/video/[^/]+/(?P<id>[a-f0-9]+)'
_TEST = { _TEST = {
'url': 'https://www.viceland.com/en_us/video/trapped/588a70d0dba8a16007de7316', 'url': 'https://www.viceland.com/en_us/video/trapped/588a70d0dba8a16007de7316',
'info_dict': { 'info_dict': {
@ -24,10 +26,13 @@ class VicelandIE(ViceBaseIE):
'skip_download': True, 'skip_download': True,
}, },
'add_ie': ['UplynkPreplay'], 'add_ie': ['UplynkPreplay'],
'skip': '404',
} }
_PREPLAY_HOST = 'www.viceland' _PREPLAY_HOST = 'www.viceland'
def _real_extract(self, url): def _real_extract(self, url):
video_id = self._match_id(url) mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
locale = mobj.group('locale')
webpage = self._download_webpage(url, video_id) webpage = self._download_webpage(url, video_id)
return self._extract_preplay_video(url, webpage) return self._extract_preplay_video(url, locale, webpage)