X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/0652569e481a8cf0995a00635ef62143fa779add..4121346dfbb2b660ded98e98069857c7a50e381f:/youtube_dl/extractor/faz.py diff --git a/youtube_dl/extractor/faz.py b/youtube_dl/extractor/faz.py index cebdd01..312ee2a 100644 --- a/youtube_dl/extractor/faz.py +++ b/youtube_dl/extractor/faz.py @@ -1,7 +1,15 @@ -# encoding: utf-8 +# coding: utf-8 from __future__ import unicode_literals +import re + from .common import InfoExtractor +from ..compat import compat_etree_fromstring +from ..utils import ( + xpath_element, + xpath_text, + int_or_none, +) class FazIE(InfoExtractor): @@ -37,31 +45,49 @@ class FazIE(InfoExtractor): video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) - config_xml_url = self._search_regex( - r'writeFLV\(\'(.+?)\',', webpage, 'config xml url') - config = self._download_xml( - config_xml_url, video_id, 'Downloading config xml') + description = self._og_search_description(webpage) + media = self._html_search_regex( + r"data-videojs-media='([^']+)", + webpage, 'media') + if media == 'extern': + perform_url = self._search_regex( + r"]+?src='((?:http:)?//player\.performgroup\.com/eplayer/eplayer\.html#/?[0-9a-f]{26}\.[0-9a-z]{26})", + webpage, 'perform url') + return self.url_result(perform_url) + config = compat_etree_fromstring(media) - 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 is not None: + encoding_url = xpath_text(encoding, 'FILENAME') + if encoding_url: + tbr = xpath_text(encoding, 'AVERAGEBITRATE', 1000) + if tbr: + tbr = int_or_none(tbr.replace(',', '.')) + f = { + 'url': encoding_url, + 'format_id': code.lower(), + 'quality': pref, + 'tbr': tbr, + 'vcodec': xpath_text(encoding, 'CODEC'), + } + mobj = re.search(r'(\d+)x(\d+)_(\d+)\.mp4', encoding_url) + if mobj: + f.update({ + 'width': int(mobj.group(1)), + 'height': int(mobj.group(2)), + 'tbr': tbr or int(mobj.group(3)), + }) + formats.append(f) self._sort_formats(formats) - descr = self._html_search_regex( - r'

(.*?)

', 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')), }