[aparat] Extract all formats (closes #13887)

This commit is contained in:
Sergey M․ 2017-08-12 17:18:23 +07:00
parent e74e3b63e3
commit 70851a95c3
No known key found for this signature in database
GPG Key ID: 2C393E0F18A9236D

View File

@ -3,13 +3,13 @@ from __future__ import unicode_literals
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import ( from ..utils import (
ExtractorError, int_or_none,
HEADRequest, mimetype2ext,
) )
class AparatIE(InfoExtractor): class AparatIE(InfoExtractor):
_VALID_URL = r'^https?://(?:www\.)?aparat\.com/(?:v/|video/video/embed/videohash/)(?P<id>[a-zA-Z0-9]+)' _VALID_URL = r'https?://(?:www\.)?aparat\.com/(?:v/|video/video/embed/videohash/)(?P<id>[a-zA-Z0-9]+)'
_TEST = { _TEST = {
'url': 'http://www.aparat.com/v/wP8On', 'url': 'http://www.aparat.com/v/wP8On',
@ -29,30 +29,41 @@ class AparatIE(InfoExtractor):
# Note: There is an easier-to-parse configuration at # Note: There is an easier-to-parse configuration at
# http://www.aparat.com/video/video/config/videohash/%video_id # http://www.aparat.com/video/video/config/videohash/%video_id
# but the URL in there does not work # but the URL in there does not work
embed_url = 'http://www.aparat.com/video/video/embed/vt/frame/showvideo/yes/videohash/' + video_id webpage = self._download_webpage(
webpage = self._download_webpage(embed_url, video_id) 'http://www.aparat.com/video/video/embed/vt/frame/showvideo/yes/videohash/' + video_id,
video_id)
file_list = self._parse_json(self._search_regex(
r'fileList\s*=\s*JSON\.parse\(\'([^\']+)\'\)', webpage, 'file list'), video_id)
for i, item in enumerate(file_list[0]):
video_url = item['file']
req = HEADRequest(video_url)
res = self._request_webpage(
req, video_id, note='Testing video URL %d' % i, errnote=False)
if res:
break
else:
raise ExtractorError('No working video URLs found')
title = self._search_regex(r'\s+title:\s*"([^"]+)"', webpage, 'title') title = self._search_regex(r'\s+title:\s*"([^"]+)"', webpage, 'title')
file_list = self._parse_json(
self._search_regex(
r'fileList\s*=\s*JSON\.parse\(\'([^\']+)\'\)', webpage,
'file list'),
video_id)
formats = []
for item in file_list[0]:
file_url = item.get('file')
if not file_url:
continue
ext = mimetype2ext(item.get('type'))
label = item.get('label')
formats.append({
'url': file_url,
'ext': ext,
'format_id': label or ext,
'height': int_or_none(self._search_regex(
r'(\d+)[pP]', label or '', 'height', default=None)),
})
self._sort_formats(formats)
thumbnail = self._search_regex( thumbnail = self._search_regex(
r'image:\s*"([^"]+)"', webpage, 'thumbnail', fatal=False) r'image:\s*"([^"]+)"', webpage, 'thumbnail', fatal=False)
return { return {
'id': video_id, 'id': video_id,
'title': title, 'title': title,
'url': video_url,
'ext': 'mp4',
'thumbnail': thumbnail, 'thumbnail': thumbnail,
'age_limit': self._family_friendly_search(webpage), 'age_limit': self._family_friendly_search(webpage),
'formats': formats,
} }