1
0
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl.git synced 2024-12-05 00:17:43 +00:00
youtube-dl/youtube_dl/extractor/bigflix.py

79 lines
2.3 KiB
Python
Raw Normal View History

# coding: utf-8
from __future__ import unicode_literals
2016-01-10 04:31:36 +00:00
import re
from .common import InfoExtractor
from ..compat import (
compat_b64decode,
compat_urllib_parse_unquote,
)
class BigflixIE(InfoExtractor):
2016-01-10 04:31:36 +00:00
_VALID_URL = r'https?://(?:www\.)?bigflix\.com/.+/(?P<id>[0-9]+)'
_TESTS = [{
2016-01-10 04:49:27 +00:00
# 2 formats
2016-01-10 04:31:36 +00:00
'url': 'http://www.bigflix.com/Tamil-movies/Drama-movies/Madarasapatinam/16070',
'info_dict': {
'id': '16070',
'ext': 'mp4',
'title': 'Madarasapatinam',
2016-07-26 14:44:53 +00:00
'description': 'md5:9f0470b26a4ba8e824c823b5d95c2f6b',
2016-01-10 04:31:36 +00:00
'formats': 'mincount:2',
},
'params': {
'skip_download': True,
}
2016-01-10 04:49:27 +00:00
}, {
# multiple formats
'url': 'http://www.bigflix.com/Malayalam-movies/Drama-movies/Indian-Rupee/15967',
'only_matching': True,
2016-01-10 04:31:36 +00:00
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
title = self._html_search_regex(
r'<div[^>]+class=["\']pagetitle["\'][^>]*>(.+?)</div>',
webpage, 'title')
2016-01-10 04:31:36 +00:00
def decode_url(quoted_b64_url):
return compat_b64decode(compat_urllib_parse_unquote(
quoted_b64_url)).decode('utf-8')
2016-01-10 04:49:27 +00:00
formats = []
for height, encoded_url in re.findall(
r'ContentURL_(\d{3,4})[pP][^=]+=([^&]+)', webpage):
2016-01-10 04:49:27 +00:00
video_url = decode_url(encoded_url)
f = {
'url': video_url,
'format_id': '%sp' % height,
'height': int(height),
}
if video_url.startswith('rtmp'):
f['ext'] = 'flv'
formats.append(f)
2016-01-10 04:31:36 +00:00
2016-01-10 04:49:27 +00:00
file_url = self._search_regex(
r'file=([^&]+)', webpage, 'video url', default=None)
if file_url:
video_url = decode_url(file_url)
if all(f['url'] != video_url for f in formats):
formats.append({
'url': decode_url(file_url),
})
2016-01-10 04:31:36 +00:00
2016-01-10 04:49:27 +00:00
self._sort_formats(formats)
description = self._html_search_meta('description', webpage)
return {
'id': video_id,
'title': title,
'description': description,
2016-01-10 04:31:36 +00:00
'formats': formats
}