yt-dlc/youtube_dl/extractor/snagfilms.py

182 lines
6.8 KiB
Python
Raw Normal View History

2015-06-27 12:20:42 +00:00
from __future__ import unicode_literals
import re
2015-06-26 17:25:43 +00:00
from .common import InfoExtractor
2015-06-27 12:20:42 +00:00
from ..utils import (
ExtractorError,
2015-06-27 12:20:42 +00:00
clean_html,
determine_ext,
int_or_none,
js_to_json,
parse_duration,
)
2015-06-26 17:25:43 +00:00
2015-06-27 12:20:42 +00:00
class SnagFilmsEmbedIE(InfoExtractor):
_VALID_URL = r'https?://(?:(?:www|embed)\.)?snagfilms\.com/embed/player\?.*\bfilmId=(?P<id>[\da-f-]{36})'
2015-06-26 23:13:14 +00:00
_TESTS = [{
2015-06-27 12:20:42 +00:00
'url': 'http://embed.snagfilms.com/embed/player?filmId=74849a00-85a9-11e1-9660-123139220831&w=500',
'md5': '2924e9215c6eff7a55ed35b72276bd93',
'info_dict': {
2015-06-26 23:13:14 +00:00
'id': '74849a00-85a9-11e1-9660-123139220831',
'ext': 'mp4',
'title': '#whilewewatch',
}
}, {
# invalid labels, 360p is better that 480p
'url': 'http://www.snagfilms.com/embed/player?filmId=17ca0950-a74a-11e0-a92a-0026bb61d036',
'md5': '882fca19b9eb27ef865efeeaed376a48',
'info_dict': {
'id': '17ca0950-a74a-11e0-a92a-0026bb61d036',
'ext': 'mp4',
'title': 'Life in Limbo',
}
2015-06-27 12:20:42 +00:00
}, {
'url': 'http://www.snagfilms.com/embed/player?filmId=0000014c-de2f-d5d6-abcf-ffef58af0017',
'only_matching': True,
2015-06-26 23:13:14 +00:00
}]
2015-06-26 17:25:43 +00:00
@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')
2015-06-26 20:50:27 +00:00
def _real_extract(self, url):
2015-06-27 12:20:42 +00:00
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
2015-06-26 17:25:43 +00:00
if '>This film is not playable in your area.<' in webpage:
raise ExtractorError(
'Film %s is not playable in your area.' % video_id, expected=True)
2015-06-26 20:50:27 +00:00
formats = []
2015-06-27 12:20:42 +00:00
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')
ext = determine_ext(file_)
format_id = source.get('label') or ext
if all(v == 'm3u8' for v in (type_, ext)):
2015-06-27 12:20:42 +00:00
formats.extend(self._extract_m3u8_formats(
file_, video_id, 'mp4', m3u8_id='hls'))
2015-06-26 20:50:27 +00:00
else:
2015-06-27 12:20:42 +00:00
bitrate = int_or_none(self._search_regex(
[r'(\d+)kbps', r'_\d{1,2}x\d{1,2}_(\d{3,})\.%s' % ext],
file_, 'bitrate', default=None))
2015-06-27 12:20:42 +00:00
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,
})
2015-06-26 20:50:27 +00:00
self._sort_formats(formats)
2015-06-26 17:25:43 +00:00
2015-06-27 12:20:42 +00:00
title = self._search_regex(
[r"title\s*:\s*'([^']+)'", r'<title>([^<]+)</title>'],
webpage, 'title')
2015-06-26 20:50:27 +00:00
return {
'id': video_id,
2015-06-27 12:20:42 +00:00
'title': title,
'formats': formats,
}
class SnagFilmsIE(InfoExtractor):
2015-06-27 12:40:01 +00:00
_VALID_URL = r'https?://(?:www\.)?snagfilms\.com/(?:films/title|show)/(?P<id>[^?#]+)'
_TESTS = [{
2015-06-27 12:20:42 +00:00
'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']
}
2015-06-27 12:40:01 +00:00
}, {
'url': 'http://www.snagfilms.com/show/the_world_cut_project/india',
'md5': 'e6292e5b837642bbda82d7f8bf3fbdfd',
'info_dict': {
'id': '00000145-d75c-d96e-a9c7-ff5c67b20000',
'display_id': 'the_world_cut_project/india',
'ext': 'mp4',
'title': 'India',
'description': 'md5:5c168c5a8f4719c146aad2e0dfac6f5f',
'thumbnail': 're:^https?://.*\.jpg',
'duration': 979,
'categories': ['Documentary', 'Sports', 'Politics']
}
2015-06-27 12:57:01 +00:00
}, {
# Film is not playable in your area.
'url': 'http://www.snagfilms.com/films/title/inside_mecca',
'only_matching': True,
}, {
# Film is not available.
'url': 'http://www.snagfilms.com/show/augie_alone/flirting',
'only_matching': True,
2015-06-27 12:40:01 +00:00
}]
2015-06-27 12:20:42 +00:00
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
if ">Sorry, the Film you're looking for is not available.<" in webpage:
raise ExtractorError(
'Film %s is not available.' % display_id, expected=True)
2015-06-27 12:20:42 +00:00
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,
2015-06-26 20:50:27 +00:00
'display_id': display_id,
'title': title,
'description': description,
2015-06-26 23:13:14 +00:00
'thumbnail': thumbnail,
2015-06-27 12:20:42 +00:00
'duration': duration,
'categories': categories,
2015-06-26 20:50:27 +00:00
}