From 0385d642232ba4e8b455d0c4eb95c7985f22f276 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sat, 30 May 2015 14:12:58 +0600 Subject: [PATCH] [crunchyroll] Extract subtitles extraction routine --- youtube_dl/extractor/crunchyroll.py | 30 +++++++++++++---------------- 1 file changed, 13 insertions(+), 17 deletions(-) diff --git a/youtube_dl/extractor/crunchyroll.py b/youtube_dl/extractor/crunchyroll.py index 1c77df47ef..4ac537a6d7 100644 --- a/youtube_dl/extractor/crunchyroll.py +++ b/youtube_dl/extractor/crunchyroll.py @@ -76,8 +76,8 @@ def _real_initialize(self): self._login() def _decrypt_subtitles(self, data, iv, id): - data = bytes_to_intlist(data) - iv = bytes_to_intlist(iv) + data = bytes_to_intlist(base64.b64decode(data)) + iv = bytes_to_intlist(base64.b64decode(iv)) id = int(id) def obfuscate_key_aux(count, modulo, start): @@ -179,6 +179,16 @@ def ass_bool(strvalue): return output + def _extract_subtitles(self, subtitle): + sub_root = xml.etree.ElementTree.fromstring(subtitle) + return [{ + 'ext': 'srt', + 'data': self._convert_subtitles_to_srt(sub_root), + }, { + 'ext': 'ass', + 'data': self._convert_subtitles_to_ass(sub_root), + }] + def _get_subtitles(self, video_id, webpage): subtitles = {} for sub_id, sub_name in re.findall(r'\?ssid=([0-9]+)" title="([^"]+)', webpage): @@ -190,25 +200,11 @@ def _get_subtitles(self, video_id, webpage): data = self._search_regex(r'([^<]+)', sub_page, 'subtitle_data', fatal=False) if not id or not iv or not data: continue - id = int(id) - iv = base64.b64decode(iv) - data = base64.b64decode(data) - subtitle = self._decrypt_subtitles(data, iv, id).decode('utf-8') lang_code = self._search_regex(r'lang_code=["\']([^"\']+)', subtitle, 'subtitle_lang_code', fatal=False) if not lang_code: continue - sub_root = xml.etree.ElementTree.fromstring(subtitle) - subtitles[lang_code] = [ - { - 'ext': 'srt', - 'data': self._convert_subtitles_to_srt(sub_root), - }, - { - 'ext': 'ass', - 'data': self._convert_subtitles_to_ass(sub_root), - }, - ] + subtitles[lang_code] = self._extract_subtitles(subtitle) return subtitles def _real_extract(self, url):