1
0
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl.git synced 2024-12-05 16:37:42 +00:00
youtube-dl/youtube_dl/extractor/movingimage.py

53 lines
1.7 KiB
Python
Raw Normal View History

2015-03-11 15:15:36 +00:00
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import (
unescapeHTML,
parse_duration,
)
class MovingImageIE(InfoExtractor):
_VALID_URL = r'https?://movingimage\.nls\.uk/film/(?P<id>\d+)'
2015-03-11 15:15:36 +00:00
_TEST = {
'url': 'http://movingimage.nls.uk/film/3561',
'md5': '4caa05c2b38453e6f862197571a7be2f',
2015-03-11 15:15:36 +00:00
'info_dict': {
'id': '3561',
'ext': 'mp4',
2015-03-11 15:15:36 +00:00
'title': 'SHETLAND WOOL',
'description': 'md5:c5afca6871ad59b4271e7704fe50ab04',
'duration': 900,
'thumbnail': r're:^https?://.*\.jpg$',
2015-03-11 15:15:36 +00:00
},
}
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
formats = self._extract_m3u8_formats(
self._html_search_regex(r'file\s*:\s*"([^"]+)"', webpage, 'm3u8 manifest URL'),
video_id, ext='mp4', entry_protocol='m3u8_native')
2015-03-11 15:15:36 +00:00
def search_field(field_name, fatal=False):
return self._search_regex(
r'<span\s+class="field_title">%s:</span>\s*<span\s+class="field_content">([^<]+)</span>' % field_name,
webpage, 'title', fatal=fatal)
title = unescapeHTML(search_field('Title', fatal=True)).strip('()[]')
description = unescapeHTML(search_field('Description'))
duration = parse_duration(search_field('Running time'))
thumbnail = self._search_regex(
r"image\s*:\s*'([^']+)'", webpage, 'thumbnail', fatal=False)
2015-03-11 15:15:36 +00:00
return {
'id': video_id,
'formats': formats,
2015-03-11 15:15:36 +00:00
'title': title,
'description': description,
'duration': duration,
'thumbnail': thumbnail,
}