midgard/youtube-dl
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

[vessel] Add support for embed urls and improve extraction

Browse source
This commit is contained in:
Sergey M․ 2016-06-09 04:00:47 +07:00
parent 411c590a1f
commit 11380753b5
No known key found for this signature in database
GPG key ID: 2C393E0F18A9236D
1 changed files with 20 additions and 7 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

27
youtube_dl/extractor/vessel.py
View file

@ -2,6 +2,7 @@
from __future__ import unicode_literals from __future__ import unicode_literals
import json import json
import re
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import ( from ..utils import (
@ -12,11 +13,11 @@ from ..utils import (
class VesselIE(InfoExtractor): class VesselIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?vessel\.com/videos/(?P<id>[0-9a-zA-Z]+)' _VALID_URL = r'https?://(?:www\.)?vessel\.com/(?:videos|embed)/(?P<id>[0-9a-zA-Z]+)'
_API_URL_TEMPLATE = 'https://www.vessel.com/api/view/items/%s' _API_URL_TEMPLATE = 'https://www.vessel.com/api/view/items/%s'
_LOGIN_URL = 'https://www.vessel.com/api/account/login' _LOGIN_URL = 'https://www.vessel.com/api/account/login'
_NETRC_MACHINE = 'vessel' _NETRC_MACHINE = 'vessel'
_TEST = { _TESTS = [{
'url': 'https://www.vessel.com/videos/HDN7G5UMs', 'url': 'https://www.vessel.com/videos/HDN7G5UMs',
'md5': '455cdf8beb71c6dd797fd2f3818d05c4', 'md5': '455cdf8beb71c6dd797fd2f3818d05c4',
'info_dict': { 'info_dict': {
@ -28,7 +29,16 @@ class VesselIE(InfoExtractor):
'description': 'Did Nvidia pull out all the stops on the Titan X, or does its performance leave something to be desired?', 'description': 'Did Nvidia pull out all the stops on the Titan X, or does its performance leave something to be desired?',
'timestamp': int, 'timestamp': int,
}, },
} }, {
'url': 'https://www.vessel.com/embed/G4U7gUJ6a?w=615&h=346',
'only_matching': True,
}]
@staticmethod
def _extract_urls(webpage):
return [url for _, url in re.findall(
r'<iframe[^>]+src=(["\'])((?:https?:)?//(?:www\.)?vessel\.com/embed/[0-9a-zA-Z]+.*?)\1',
webpage)]
@staticmethod @staticmethod
def make_json_request(url, data): def make_json_request(url, data):
@ -98,16 +108,19 @@ class VesselIE(InfoExtractor):
formats = [] formats = []
for f in video_asset.get('sources', []): for f in video_asset.get('sources', []):
if f['name'] == 'hls-index': location = f.get('location')
if not location:
continue
if f.get('name') == 'hls-index':
formats.extend(self._extract_m3u8_formats( formats.extend(self._extract_m3u8_formats(
f['location'], video_id, ext='mp4', m3u8_id='m3u8')) location, video_id, ext='mp4', m3u8_id='m3u8'))
else: else:
formats.append({ formats.append({
'format_id': f['name'], 'format_id': f.get('name'),
'tbr': f.get('bitrate'), 'tbr': f.get('bitrate'),
'height': f.get('height'), 'height': f.get('height'),
'width': f.get('width'), 'width': f.get('width'),
'url': f['location'], 'url': location,
}) })
self._sort_formats(formats) self._sort_formats(formats)