From 065216d94f59953a228d2683d3bafe4241fd1e29 Mon Sep 17 00:00:00 2001 From: remitamine Date: Fri, 29 Apr 2016 11:46:42 +0100 Subject: [PATCH] [crunchyroll] reduce requests for formats extraction --- youtube_dl/extractor/crunchyroll.py | 14 ++++++++++++-- 1 file changed, 12 insertions(+), 2 deletions(-) diff --git a/youtube_dl/extractor/crunchyroll.py b/youtube_dl/extractor/crunchyroll.py index dd753c7c3..184ba6896 100644 --- a/youtube_dl/extractor/crunchyroll.py +++ b/youtube_dl/extractor/crunchyroll.py @@ -26,6 +26,7 @@ from ..utils import ( unified_strdate, urlencode_postdata, xpath_text, + extract_attributes, ) from ..aes import ( aes_cbc_decrypt, @@ -305,9 +306,18 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text r']+href="/publisher/[^"]+"[^>]*>([^<]+)', webpage, 'video_uploader', fatal=False) - formats = [] + available_fmts = [] + for a, fmt in re.findall(r'(]+token="showmedia\.([0-9]{3,4})p"[^>]+>.*?)', webpage): + attrs = extract_attributes(a) + href = attrs.get('href') + if href and '/freetrial' in href: + continue + available_fmts.append(fmt) + if not available_fmts: + available_fmts = re.findall(r'token="showmedia\.([0-9]{3,4})p"', webpage) video_encode_ids = [] - for fmt in re.findall(r'token="showmedia\.([0-9]{3,4})p"', webpage): + formats = [] + for fmt in available_fmts: stream_quality, stream_format = self._FORMAT_IDS[fmt] video_format = fmt + 'p' streamdata_req = sanitized_Request( -- 2.39.5