mirror of https://github.com/yt-dlp/yt-dlp
[mojvideo] Switch to API, handle errors, remove faked width and height
parent
37edd7dd4a
commit
b42a2a720b
@ -1,41 +1,58 @@
|
|||||||
# coding: utf-8
|
# coding: utf-8
|
||||||
from __future__ import unicode_literals
|
from __future__ import unicode_literals
|
||||||
|
|
||||||
import re
|
import re
|
||||||
|
|
||||||
from .common import InfoExtractor
|
from .common import InfoExtractor
|
||||||
|
from ..utils import (
|
||||||
|
ExtractorError,
|
||||||
|
parse_duration,
|
||||||
|
)
|
||||||
|
|
||||||
|
|
||||||
class MojvideoIE(InfoExtractor):
|
class MojvideoIE(InfoExtractor):
|
||||||
_VALID_URL = r'https?://(?:www\.)?mojvideo\.com/video-.*/(?P<id>[a-f0-9]+)'
|
_VALID_URL = r'https?://(?:www\.)?mojvideo\.com/video-(?P<display_id>[^/]+)/(?P<id>[a-f0-9]+)'
|
||||||
_TEST = {
|
_TEST = {
|
||||||
'url': 'http://www.mojvideo.com/video-v-avtu-pred-mano-rdecelaska-alfi-nipic/3d1ed4497707730b2906',
|
'url': 'http://www.mojvideo.com/video-v-avtu-pred-mano-rdecelaska-alfi-nipic/3d1ed4497707730b2906',
|
||||||
'md5': 'f7fd662cc8ce2be107b0d4f2c0483ae7',
|
'md5': 'f7fd662cc8ce2be107b0d4f2c0483ae7',
|
||||||
'info_dict': {
|
'info_dict': {
|
||||||
'id': '3d1ed4497707730b2906',
|
'id': '3d1ed4497707730b2906',
|
||||||
|
'display_id': 'v-avtu-pred-mano-rdecelaska-alfi-nipic',
|
||||||
'ext': 'mp4',
|
'ext': 'mp4',
|
||||||
'title': 'V avtu pred mano rdečelaska - Alfi Nipič',
|
'title': 'V avtu pred mano rdečelaska - Alfi Nipič',
|
||||||
'description':'Video: V avtu pred mano rdečelaska - Alfi Nipič',
|
'thumbnail': 're:^http://.*\.jpg$',
|
||||||
'height':378,
|
'duration': 242,
|
||||||
'width':480
|
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
def _real_extract(self, url):
|
def _real_extract(self, url):
|
||||||
mobj = re.match(self._VALID_URL, url)
|
mobj = re.match(self._VALID_URL, url)
|
||||||
video_id = mobj.group('id')
|
video_id = mobj.group('id')
|
||||||
|
display_id = mobj.group('display_id')
|
||||||
|
|
||||||
|
# XML is malformed
|
||||||
|
playerapi = self._download_webpage(
|
||||||
|
'http://www.mojvideo.com/playerapi.php?v=%s&t=1' % video_id, display_id)
|
||||||
|
|
||||||
webpage = self._download_webpage(url, video_id)
|
if '<error>true</error>' in playerapi:
|
||||||
title = self._html_search_regex(r'<title>(.*?)</title>', webpage, 'title')
|
error_desc = self._html_search_regex(
|
||||||
description = self._search_regex(r'<meta name="description" content="(.*)" />', webpage, 'video description')
|
r'<errordesc>([^<]*)</errordesc>', playerapi, 'error description', fatal=False)
|
||||||
final_url = self._html_search_regex(r'mp4: \'(.*)\'', webpage, 'video url')
|
raise ExtractorError('%s said: %s' % (self.IE_NAME, error_desc), expected=True)
|
||||||
height=int(self._search_regex(r'<meta name="video_height" content="([0-9]*)" />',webpage,"video height"))
|
|
||||||
width=int(self._search_regex(r'<meta name="video_width" content="([0-9]*)" />',webpage,"video width"))
|
title = self._html_search_regex(
|
||||||
|
r'<title>([^<]+)</title>', playerapi, 'title')
|
||||||
|
video_url = self._html_search_regex(
|
||||||
|
r'<file>([^<]+)</file>', playerapi, 'video URL')
|
||||||
|
thumbnail = self._html_search_regex(
|
||||||
|
r'<preview>([^<]+)</preview>', playerapi, 'thumbnail', fatal=False)
|
||||||
|
duration = parse_duration(self._html_search_regex(
|
||||||
|
r'<duration>([^<]+)</duration>', playerapi, 'duration', fatal=False))
|
||||||
|
|
||||||
return {
|
return {
|
||||||
'id': video_id,
|
'id': video_id,
|
||||||
|
'display_id': display_id,
|
||||||
|
'url': video_url,
|
||||||
'title': title,
|
'title': title,
|
||||||
'description': description,
|
'thumbnail': thumbnail,
|
||||||
'ext': 'mp4',
|
'duration': duration,
|
||||||
'url': final_url,
|
|
||||||
'height':height,
|
|
||||||
'width':width
|
|
||||||
}
|
}
|
Loading…
Reference in New Issue