Add hls and dash formats.
This commit is contained in:
Kyle
parent
94b27f66ef
commit
9aff332b53
@ -2,7 +2,14 @@
|
||||
from __future__ import unicode_literals
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import int_or_none, mimetype2ext, str_or_none, try_get, url_or_none
|
||||
from ..utils import (
|
||||
determine_ext,
|
||||
int_or_none,
|
||||
mimetype2ext,
|
||||
str_or_none,
|
||||
try_get,
|
||||
url_or_none,
|
||||
)
|
||||
|
||||
|
||||
class CriterionIE(InfoExtractor):
|
||||
@ -10,7 +17,6 @@ class CriterionIE(InfoExtractor):
|
||||
_TESTS = [
|
||||
{
|
||||
'url': 'http://www.criterion.com/films/184-le-samourai',
|
||||
'md5': 'e80a6ec09375c58e0050b809238c4d39',
|
||||
'info_dict': {
|
||||
'id': '265399901',
|
||||
'title': 'Le samouraï',
|
||||
@ -18,10 +24,10 @@ class CriterionIE(InfoExtractor):
|
||||
'description': 'md5:56ad66935158c6c88d4e391397c00d22',
|
||||
'thumbnail': r're:^https?://.*\.jpg$',
|
||||
},
|
||||
'params': {'skip_download': True},
|
||||
},
|
||||
{
|
||||
'url': 'https://www.criterion.com/films/28986-the-heiress',
|
||||
'md5': '7178b368986eed7c9bf362dd90472c74',
|
||||
'info_dict': {
|
||||
'id': '315291282',
|
||||
'title': 'The Heiress',
|
||||
@ -29,10 +35,10 @@ class CriterionIE(InfoExtractor):
|
||||
'description': 'md5:3d34fe5e6ff5520998b13137eba0f7ce',
|
||||
'thumbnail': r're:^https?://.*\.jpg$',
|
||||
},
|
||||
'params': {'skip_download': True},
|
||||
},
|
||||
{
|
||||
'url': 'https://www.criterion.com/films/28836-funny-games',
|
||||
'md5': '6e36a90749755e600eeb57dc632e920d',
|
||||
'info_dict': {
|
||||
'id': '316586307',
|
||||
'title': 'Funny Games',
|
||||
@ -40,10 +46,10 @@ class CriterionIE(InfoExtractor):
|
||||
'description': 'md5:64326c0cd08a6a582c10d63349941250',
|
||||
'thumbnail': r're:^https?://.*\.jpg$',
|
||||
},
|
||||
'params': {'skip_download': True},
|
||||
},
|
||||
{
|
||||
'url': 'https://www.criterion.com/films/613-the-magic-flute',
|
||||
'md5': '8458ac11d5809f3f2d8f9aec1afa2fd6',
|
||||
'info_dict': {
|
||||
'id': '305845790',
|
||||
'title': 'The Magic Flute',
|
||||
@ -51,12 +57,66 @@ class CriterionIE(InfoExtractor):
|
||||
'description': 'md5:9f232dcf15d9861c6a551662973482a5',
|
||||
'thumbnail': r're:^https?://.*\.jpg$',
|
||||
},
|
||||
'params': {'skip_download': True},
|
||||
},
|
||||
]
|
||||
|
||||
def _extract_embedded_url(self, pattern, html, group):
|
||||
return self._search_regex(pattern, html, 'embedded url', group=group)
|
||||
|
||||
def _extract_formats_from_stream(self, data, final_id):
|
||||
ext_formats = []
|
||||
if isinstance(data, dict):
|
||||
cdns = data.get('cdns')
|
||||
if cdns:
|
||||
for cdn_name, cdn_data in cdns.items():
|
||||
url = url_or_none(cdn_data.get('url'))
|
||||
|
||||
ext = determine_ext(url)
|
||||
|
||||
if ext == 'm3u8':
|
||||
ext_formats.extend(
|
||||
self._extract_m3u8_formats(
|
||||
url,
|
||||
final_id,
|
||||
ext='mp4',
|
||||
m3u8_id=str_or_none(cdn_name) or 'hls',
|
||||
fatal=False,
|
||||
)
|
||||
)
|
||||
# dash mpd
|
||||
if ext == 'json':
|
||||
ext_formats.extend(
|
||||
self._extract_mpd_formats(
|
||||
url.replace('master.json', 'master.mpd'),
|
||||
final_id,
|
||||
mpd_id=cdn_name,
|
||||
fatal=False,
|
||||
)
|
||||
)
|
||||
return ext_formats
|
||||
|
||||
def _extract_formats_from_other(self, src, data):
|
||||
if not isinstance(data, list):
|
||||
data = [data]
|
||||
ext_formats = []
|
||||
if src == 'progressive':
|
||||
for vid in data:
|
||||
profile = str_or_none(vid.get('profile'))
|
||||
ext_formats.append(
|
||||
{
|
||||
'url': url_or_none(vid.get('url')),
|
||||
'ext': mimetype2ext(vid.get('mime')),
|
||||
'format_id': vid.get('cdn') + (profile if profile else ''),
|
||||
'height': int_or_none(vid.get('height')),
|
||||
'width': int_or_none(vid.get('width')),
|
||||
'fps': int_or_none(vid.get('fps')),
|
||||
}
|
||||
)
|
||||
vid_id = vid.get('id') or ''
|
||||
self.to_screen('%s: Downloading mp4 information' % (vid_id,))
|
||||
return ext_formats
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
@ -81,7 +141,7 @@ class CriterionIE(InfoExtractor):
|
||||
embedded_url, embedded_id, headers={'Referer': url}
|
||||
)
|
||||
|
||||
# Parse json data
|
||||
# Grab json data
|
||||
data_re = r'var\s*config\s*=\s*(?P<data>.*?);'
|
||||
data_str = self._search_regex(
|
||||
data_re, embedded_webpage, 'json data', group='data'
|
||||
@ -90,23 +150,26 @@ class CriterionIE(InfoExtractor):
|
||||
|
||||
final_id = str_or_none(try_get(data, lambda x: x['video']['id']))
|
||||
|
||||
videos = try_get(data, lambda x: x['request']['files']['progressive'], list)
|
||||
stream_types = ('hls', 'dash',)
|
||||
nonstream_types = ('progressive',)
|
||||
|
||||
# Collect formats
|
||||
formats = []
|
||||
for vid in videos:
|
||||
formats.append(
|
||||
{
|
||||
'url': url_or_none(vid.get('url')),
|
||||
'ext': mimetype2ext(vid.get('mime')),
|
||||
'resolution': str_or_none(vid.get('quality')),
|
||||
'height': int_or_none(vid.get('height')),
|
||||
'width': int_or_none(vid.get('width')),
|
||||
'fps': int_or_none(vid.get('fps')),
|
||||
}
|
||||
sources = try_get(data, lambda x: x['request']['files'], dict)
|
||||
if sources:
|
||||
for src, src_data in sources.items():
|
||||
if src in stream_types:
|
||||
formats.extend(
|
||||
self._extract_formats_from_stream(src_data, final_id)
|
||||
)
|
||||
formats.sort(key=lambda x: x['height'])
|
||||
elif src in nonstream_types:
|
||||
formats.extend(self._extract_formats_from_other(src, src_data))
|
||||
|
||||
self._sort_formats(formats)
|
||||
|
||||
thumb_data = try_get(data, lambda x: x['video']['thumbs'], dict)
|
||||
thumbnails = []
|
||||
if thumb_data:
|
||||
for url in thumb_data:
|
||||
thumbnails.append({'url': url_or_none(thumb_data[url])})
|
||||
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user