From 74c42d9ec3c6e0f0f67923fd151ce2531637a3db Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sun, 15 Oct 2017 06:13:48 +0700 Subject: [PATCH] [downloader/hls] Ignore anvato ad fragments (closes #14496) --- youtube_dl/downloader/hls.py | 28 ++++++++++++++++++++++++---- 1 file changed, 24 insertions(+), 4 deletions(-) diff --git a/youtube_dl/downloader/hls.py b/youtube_dl/downloader/hls.py index 46308cf07..7955ca510 100644 --- a/youtube_dl/downloader/hls.py +++ b/youtube_dl/downloader/hls.py @@ -75,15 +75,29 @@ def real_download(self, filename, info_dict): fd.add_progress_hook(ph) return fd.real_download(filename, info_dict) - total_frags = 0 + def anvato_ad(s): + return s.startswith('#ANVATO-SEGMENT-INFO') and 'type=ad' in s + + media_frags = 0 + ad_frags = 0 + ad_frag_next = False for line in s.splitlines(): line = line.strip() - if line and not line.startswith('#'): - total_frags += 1 + if not line: + continue + if line.startswith('#'): + if anvato_ad(line): + ad_frags += 1 + continue + if ad_frag_next: + ad_frag_next = False + continue + media_frags += 1 ctx = { 'filename': filename, - 'total_frags': total_frags, + 'total_frags': media_frags, + 'ad_frags': ad_frags, } self._prepare_and_start_frag_download(ctx) @@ -101,10 +115,14 @@ def real_download(self, filename, info_dict): decrypt_info = {'METHOD': 'NONE'} byte_range = {} frag_index = 0 + ad_frag_next = False for line in s.splitlines(): line = line.strip() if line: if not line.startswith('#'): + if ad_frag_next: + ad_frag_next = False + continue frag_index += 1 if frag_index <= ctx['fragment_index']: continue @@ -175,6 +193,8 @@ def real_download(self, filename, info_dict): 'start': sub_range_start, 'end': sub_range_start + int(splitted_byte_range[0]), } + elif anvato_ad(line): + ad_frag_next = True self._finish_frag_download(ctx)