Merge branch 'remitamine-snagfilms'

This commit is contained in:
Sergey M․ 2015-06-27 18:29:16 +06:00
commit 9d1bf70234
3 changed files with 159 additions and 0 deletions

View file

@ -493,6 +493,10 @@ from .smotri import (
SmotriUserIE, SmotriUserIE,
SmotriBroadcastIE, SmotriBroadcastIE,
) )
from .snagfilms import (
SnagFilmsIE,
SnagFilmsEmbedIE,
)
from .snotr import SnotrIE from .snotr import SnotrIE
from .sohu import SohuIE from .sohu import SohuIE
from .soompi import ( from .soompi import (

View file

@ -47,6 +47,7 @@ from .xhamster import XHamsterEmbedIE
from .vimeo import VimeoIE from .vimeo import VimeoIE
from .dailymotion import DailymotionCloudIE from .dailymotion import DailymotionCloudIE
from .onionstudios import OnionStudiosIE from .onionstudios import OnionStudiosIE
from .snagfilms import SnagFilmsEmbedIE
class GenericIE(InfoExtractor): class GenericIE(InfoExtractor):
@ -849,6 +850,15 @@ class GenericIE(InfoExtractor):
'uploader_id': 'clickhole', 'uploader_id': 'clickhole',
} }
}, },
# SnagFilms embed
{
'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
'info_dict': {
'id': '74849a00-85a9-11e1-9660-123139220831',
'ext': 'mp4',
'title': '#whilewewatch',
}
},
# AdobeTVVideo embed # AdobeTVVideo embed
{ {
'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners', 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
@ -1550,6 +1560,11 @@ class GenericIE(InfoExtractor):
if onionstudios_url: if onionstudios_url:
return self.url_result(onionstudios_url) return self.url_result(onionstudios_url)
# Look for SnagFilms embeds
snagfilms_url = SnagFilmsEmbedIE._extract_url(webpage)
if snagfilms_url:
return self.url_result(snagfilms_url)
# Look for AdobeTVVideo embeds # Look for AdobeTVVideo embeds
mobj = re.search( mobj = re.search(
r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]', r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',

View file

@ -0,0 +1,140 @@
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
clean_html,
determine_ext,
int_or_none,
js_to_json,
parse_duration,
)
class SnagFilmsEmbedIE(InfoExtractor):
_VALID_URL = r'https?://(?:(?:www|embed)\.)?snagfilms\.com/embed/player\?.*\bfilmId=(?P<id>[\da-f-]{36})'
_TESTS = [{
'url': 'http://embed.snagfilms.com/embed/player?filmId=74849a00-85a9-11e1-9660-123139220831&w=500',
'md5': '2924e9215c6eff7a55ed35b72276bd93',
'info_dict': {
'id': '74849a00-85a9-11e1-9660-123139220831',
'ext': 'mp4',
'title': '#whilewewatch',
}
}, {
'url': 'http://www.snagfilms.com/embed/player?filmId=0000014c-de2f-d5d6-abcf-ffef58af0017',
'only_matching': True,
}]
@staticmethod
def _extract_url(webpage):
mobj = re.search(
r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:embed\.)?snagfilms\.com/embed/player.+?)\1', webpage)
if mobj:
return mobj.group('url')
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
formats = []
for source in self._parse_json(js_to_json(self._search_regex(
r'(?s)sources:\s*(\[.+?\]),', webpage, 'json')), video_id):
file_ = source.get('file')
if not file_:
continue
type_ = source.get('type')
format_id = source.get('label')
ext = determine_ext(file_)
if any(_ == 'm3u8' for _ in (type_, ext)):
formats.extend(self._extract_m3u8_formats(
file_, video_id, 'mp4', m3u8_id='hls'))
else:
bitrate = int_or_none(self._search_regex(
r'(\d+)kbps', file_, 'bitrate', default=None))
height = int_or_none(self._search_regex(
r'^(\d+)[pP]$', format_id, 'height', default=None))
formats.append({
'url': file_,
'format_id': format_id,
'tbr': bitrate,
'height': height,
})
self._sort_formats(formats)
title = self._search_regex(
[r"title\s*:\s*'([^']+)'", r'<title>([^<]+)</title>'],
webpage, 'title')
return {
'id': video_id,
'title': title,
'formats': formats,
}
class SnagFilmsIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?snagfilms\.com/films/title/(?P<id>[^/]+)'
_TEST = {
'url': 'http://www.snagfilms.com/films/title/lost_for_life',
'md5': '19844f897b35af219773fd63bdec2942',
'info_dict': {
'id': '0000014c-de2f-d5d6-abcf-ffef58af0017',
'display_id': 'lost_for_life',
'ext': 'mp4',
'title': 'Lost for Life',
'description': 'md5:fbdacc8bb6b455e464aaf98bc02e1c82',
'thumbnail': 're:^https?://.*\.jpg',
'duration': 4489,
'categories': ['Documentary', 'Crime', 'Award Winning', 'Festivals']
}
}
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
film_id = self._search_regex(r'filmId=([\da-f-]{36})"', webpage, 'film id')
snag = self._parse_json(
self._search_regex(
'Snag\.page\.data\s*=\s*(\[.+?\]);', webpage, 'snag'),
display_id)
for item in snag:
if item.get('data', {}).get('film', {}).get('id') == film_id:
data = item['data']['film']
title = data['title']
description = clean_html(data.get('synopsis'))
thumbnail = data.get('image')
duration = int_or_none(data.get('duration') or data.get('runtime'))
categories = [
category['title'] for category in data.get('categories', [])
if category.get('title')]
break
else:
title = self._search_regex(
r'itemprop="title">([^<]+)<', webpage, 'title')
description = self._html_search_regex(
r'(?s)<div itemprop="description" class="film-synopsis-inner ">(.+?)</div>',
webpage, 'description', default=None) or self._og_search_description(webpage)
thumbnail = self._og_search_thumbnail(webpage)
duration = parse_duration(self._search_regex(
r'<span itemprop="duration" class="film-duration strong">([^<]+)<',
webpage, 'duration', fatal=False))
categories = re.findall(r'<a href="/movies/[^"]+">([^<]+)</a>', webpage)
return {
'_type': 'url_transparent',
'url': 'http://embed.snagfilms.com/embed/player?filmId=%s' % film_id,
'id': film_id,
'display_id': display_id,
'title': title,
'description': description,
'thumbnail': thumbnail,
'duration': duration,
'categories': categories,
}