w/youtube-dl
1
0
Fork 0
Code Issues Pull requests Releases Wiki Activity

[faz] extract duration and bitrate and use xpath_element and xpath_text for extraction

Browse source
This commit is contained in:
remitamine 2015-12-20 21:38:30 +01:00
parent c240ab6ecf
commit ecbccea703
1 changed files with 21 additions and 15 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

26
youtube_dl/extractor/faz.py
View file

@ -2,6 +2,11 @@
from __future__ import unicode_literals from __future__ import unicode_literals
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import (
xpath_element,
xpath_text,
int_or_none,
)
class FazIE(InfoExtractor): class FazIE(InfoExtractor):
@ -37,31 +42,32 @@ class FazIE(InfoExtractor):
video_id = self._match_id(url) video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id) webpage = self._download_webpage(url, video_id)
description = self._og_search_description(webpage)
config_xml_url = self._search_regex( 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 = self._download_xml(
config_xml_url, video_id, 'Downloading config xml') config_xml_url, video_id, 'Downloading config xml')
encodings = config.find('ENCODINGS') encodings = xpath_element(config, 'ENCODINGS', 'encodings', True)
formats = [] formats = []
for pref, code in enumerate(['LOW', 'HIGH', 'HQ']): for pref, code in enumerate(['LOW', 'HIGH', 'HQ']):
encoding = encodings.find(code) encoding = xpath_element(encodings, code)
if encoding is None: if encoding:
continue encoding_url = xpath_text(encoding, 'FILENAME')
encoding_url = encoding.find('FILENAME').text if encoding_url:
formats.append({ formats.append({
'url': encoding_url, 'url': encoding_url,
'format_id': code.lower(), 'format_id': code.lower(),
'quality': pref, 'quality': pref,
'tbr': int_or_none(xpath_text(encoding, 'AVERAGEBITRATE')),
}) })
self._sort_formats(formats) self._sort_formats(formats)
descr = self._html_search_regex(
r'<p class="Content Copy">(.*?)</p>', webpage, 'description', fatal=False)
return { return {
'id': video_id, 'id': video_id,
'title': self._og_search_title(webpage), 'title': self._og_search_title(webpage),
'formats': formats, 'formats': formats,
'description': descr, 'description': description.strip() if description else None,
'thumbnail': config.find('STILL/STILL_BIG').text, 'thumbnail': xpath_text(config, 'STILL/STILL_BIG'),
'duration': int_or_none(xpath_text(config, 'DURATION')),
} }