|
|
@ -4,11 +4,10 @@ from __future__ import unicode_literals |
|
|
|
import re |
|
|
|
|
|
|
|
from .common import InfoExtractor |
|
|
|
from ..utils import ExtractorError |
|
|
|
|
|
|
|
|
|
|
|
class TheOnionIE(InfoExtractor): |
|
|
|
_VALID_URL = r'(?x)https?://(?:www\.)?theonion\.com/video/[^,]+,(?P<article_id>[0-9]+)/?' |
|
|
|
_VALID_URL = r'https?://(?:www\.)?theonion\.com/video/[^,]+,(?P<id>[0-9]+)/?' |
|
|
|
_TEST = { |
|
|
|
'url': 'http://www.theonion.com/video/man-wearing-mm-jacket-gods-image,36918/', |
|
|
|
'md5': '19eaa9a39cf9b9804d982e654dc791ee', |
|
|
@ -22,10 +21,8 @@ class TheOnionIE(InfoExtractor): |
|
|
|
} |
|
|
|
|
|
|
|
def _real_extract(self, url): |
|
|
|
mobj = re.match(self._VALID_URL, url) |
|
|
|
article_id = mobj.group('article_id') |
|
|
|
|
|
|
|
webpage = self._download_webpage(url, article_id) |
|
|
|
display_id = self._match_id(url) |
|
|
|
webpage = self._download_webpage(url, display_id) |
|
|
|
|
|
|
|
video_id = self._search_regex( |
|
|
|
r'"videoId":\s(\d+),', webpage, 'video ID') |
|
|
@ -34,10 +31,6 @@ class TheOnionIE(InfoExtractor): |
|
|
|
thumbnail = self._og_search_thumbnail(webpage) |
|
|
|
|
|
|
|
sources = re.findall(r'<source src="([^"]+)" type="([^"]+)"', webpage) |
|
|
|
if not sources: |
|
|
|
raise ExtractorError( |
|
|
|
'No sources found for video %s' % video_id, expected=True) |
|
|
|
|
|
|
|
formats = [] |
|
|
|
for src, type_ in sources: |
|
|
|
if type_ == 'video/mp4': |
|
|
@ -54,15 +47,15 @@ class TheOnionIE(InfoExtractor): |
|
|
|
}) |
|
|
|
elif type_ == 'application/x-mpegURL': |
|
|
|
formats.extend( |
|
|
|
self._extract_m3u8_formats(src, video_id, preference=-1)) |
|
|
|
self._extract_m3u8_formats(src, display_id, preference=-1)) |
|
|
|
else: |
|
|
|
self.report_warning( |
|
|
|
'Encountered unexpected format: %s' % type_) |
|
|
|
|
|
|
|
self._sort_formats(formats) |
|
|
|
|
|
|
|
return { |
|
|
|
'id': video_id, |
|
|
|
'display_id': display_id, |
|
|
|
'title': title, |
|
|
|
'formats': formats, |
|
|
|
'thumbnail': thumbnail, |
|
|
|