mirror of
https://github.com/yt-dlp/yt-dlp.git
synced 2024-12-28 09:11:48 +00:00
[faz] extract duration and bitrate and use xpath_element and xpath_text for extraction
This commit is contained in:
parent
c240ab6ecf
commit
ecbccea703
1 changed files with 21 additions and 15 deletions
|
@ -2,6 +2,11 @@
|
|||
from __future__ import unicode_literals
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
xpath_element,
|
||||
xpath_text,
|
||||
int_or_none,
|
||||
)
|
||||
|
||||
|
||||
class FazIE(InfoExtractor):
|
||||
|
@ -37,31 +42,32 @@ def _real_extract(self, url):
|
|||
video_id = self._match_id(url)
|
||||
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
description = self._og_search_description(webpage)
|
||||
config_xml_url = self._search_regex(
|
||||
r'(?:var\s+)?videoXMLURL\s*=\s*"([^"]+)', webpage, 'config xml url')
|
||||
r'videoXMLURL\s*=\s*"([^"]+)', webpage, 'config xml url')
|
||||
config = self._download_xml(
|
||||
config_xml_url, video_id, 'Downloading config xml')
|
||||
|
||||
encodings = config.find('ENCODINGS')
|
||||
encodings = xpath_element(config, 'ENCODINGS', 'encodings', True)
|
||||
formats = []
|
||||
for pref, code in enumerate(['LOW', 'HIGH', 'HQ']):
|
||||
encoding = encodings.find(code)
|
||||
if encoding is None:
|
||||
continue
|
||||
encoding_url = encoding.find('FILENAME').text
|
||||
formats.append({
|
||||
'url': encoding_url,
|
||||
'format_id': code.lower(),
|
||||
'quality': pref,
|
||||
})
|
||||
encoding = xpath_element(encodings, code)
|
||||
if encoding:
|
||||
encoding_url = xpath_text(encoding, 'FILENAME')
|
||||
if encoding_url:
|
||||
formats.append({
|
||||
'url': encoding_url,
|
||||
'format_id': code.lower(),
|
||||
'quality': pref,
|
||||
'tbr': int_or_none(xpath_text(encoding, 'AVERAGEBITRATE')),
|
||||
})
|
||||
self._sort_formats(formats)
|
||||
|
||||
descr = self._html_search_regex(
|
||||
r'<p class="Content Copy">(.*?)</p>', webpage, 'description', fatal=False)
|
||||
return {
|
||||
'id': video_id,
|
||||
'title': self._og_search_title(webpage),
|
||||
'formats': formats,
|
||||
'description': descr,
|
||||
'thumbnail': config.find('STILL/STILL_BIG').text,
|
||||
'description': description.strip() if description else None,
|
||||
'thumbnail': xpath_text(config, 'STILL/STILL_BIG'),
|
||||
'duration': int_or_none(xpath_text(config, 'DURATION')),
|
||||
}
|
||||
|
|
Loading…
Reference in a new issue