# encoding: utf-8
import re
-import xml.etree.ElementTree
from .common import InfoExtractor
from ..utils import (
determine_ext,
- clean_html,
- get_element_by_attribute,
)
webpage = self._download_webpage(url, video_id)
config_xml_url = self._search_regex(r'writeFLV\(\'(.+?)\',', webpage,
u'config xml url')
- config_xml = self._download_webpage(config_xml_url, video_id,
+ config = self._download_xml(config_xml_url, video_id,
u'Downloading config xml')
- config = xml.etree.ElementTree.fromstring(config_xml.encode('utf-8'))
encodings = config.find('ENCODINGS')
formats = []
'format_id': code.lower(),
})
- descr_html = get_element_by_attribute('class', 'Content Copy', webpage)
- info = {
+ descr = self._html_search_regex(r'<p class="Content Copy">(.*?)</p>', webpage, u'description')
+ return {
'id': video_id,
'title': self._og_search_title(webpage),
'formats': formats,
- 'description': clean_html(descr_html),
+ 'description': descr,
'thumbnail': config.find('STILL/STILL_BIG').text,
}
- # TODO: Remove when #980 has been merged
- info.update(formats[-1])
- return info