From 44783b295b5911a8c1e29a0890acad49de6a2348 Mon Sep 17 00:00:00 2001 From: edward Date: Mon, 10 Aug 2020 19:20:35 +0800 Subject: [PATCH 1/2] =?UTF-8?q?1.=20=E6=94=AF=E6=8C=81b=E7=AB=99=E5=AD=97?= =?UTF-8?q?=E5=B9=95=E4=B8=8B=E8=BD=BD=20=202.=20=E4=B8=8D=E4=B8=8B?= =?UTF-8?q?=E5=BC=B9=E5=B9=95=20=203.=20b=E7=AB=99=E5=8F=AF=E8=83=BD?= =?UTF-8?q?=E6=8F=8F=E8=BF=B0=E5=BE=88=E9=95=BF=E6=97=B6=E6=97=A0=E6=B3=95?= =?UTF-8?q?=E4=B8=8B=E8=BD=BD=E6=96=87=E4=BB=B6?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- src/you_get/extractor.py | 6 ---- src/you_get/extractors/bilibili.py | 57 ++++++++++++++++++++++++++++++ src/you_get/util/fs.py | 2 +- 3 files changed, 58 insertions(+), 7 deletions(-) diff --git a/src/you_get/extractor.py b/src/you_get/extractor.py index c4315935e7..83742f0fab 100644 --- a/src/you_get/extractor.py +++ b/src/you_get/extractor.py @@ -253,12 +253,6 @@ def download(self, **kwargs): x.write(srt) print('Done.') - if self.danmaku is not None and not dry_run: - filename = '{}.cmt.xml'.format(get_filename(self.title)) - print('Downloading {} ...\n'.format(filename)) - with open(os.path.join(kwargs['output_dir'], filename), 'w', encoding='utf8') as fp: - fp.write(self.danmaku) - if self.lyrics is not None and not dry_run: filename = '{}.lrc'.format(get_filename(self.title)) print('Downloading {} ...\n'.format(filename)) diff --git a/src/you_get/extractors/bilibili.py b/src/you_get/extractors/bilibili.py index 94e5479f65..620b0ff535 100644 --- a/src/you_get/extractors/bilibili.py +++ b/src/you_get/extractors/bilibili.py @@ -1,5 +1,6 @@ #!/usr/bin/env python +import math from ..common import * from ..extractor import VideoExtractor @@ -131,6 +132,8 @@ def url_size(url, faker=False, headers={},err_value=0): except: return err_value + # https://api.bilibili.com/x/player.so?id=cid%3A162260003&aid=95051759&bvid=BV1zE411T7nb&buvid=FB2BB46F-B1F3-4BDA-A589-33348940411A155830infoc + def prepare(self, **kwargs): self.stream_qualities = {s['quality']: s for s in self.stream_types} @@ -569,6 +572,21 @@ def extract(self, **kwargs): # extract stream with the best quality stream_id = self.streams_sorted[0]['id'] + def formattime(t): + if t/10 == 0: + return '0'+str(t) + else: + return str(t) + + def ms2time(t): + m = t/60000 + t = t%60000 + s = t/1000 + t = t%1000 + minsec = formattime(m)+':'+formattime(s)+'.'+str(t) + return minsec + + def download_playlist_by_url(self, url, **kwargs): self.url = url kwargs['playlist'] = True @@ -664,12 +682,51 @@ def download_playlist_by_url(self, url, **kwargs): p = int(match1(self.url, r'[\?&]p=(\d+)') or match1(self.url, r'/index_(\d+)') or '1')-1 for pi in range(p,pn): self.prepare_by_cid(aid,initial_state['videoData']['pages'][pi]['cid'],'%s (P%s. %s)' % (initial_state['videoData']['title'], pi+1, initial_state['videoData']['pages'][pi]['part']),html_content,playinfo,playinfo_,url) + tttt = self.title try: self.streams_sorted = [dict([('id', stream_type['id'])] + list(self.streams[stream_type['id']].items())) for stream_type in self.__class__.stream_types if stream_type['id'] in self.streams] except: self.streams_sorted = [dict([('itag', stream_type['itag'])] + list(self.streams[stream_type['itag']].items())) for stream_type in self.__class__.stream_types if stream_type['itag'] in self.streams] self.extract(**kwargs) self.download(**kwargs) + lrcurl = "https://api.bilibili.com/x/player.so?id=cid%3A" + str(initial_state['videoData']['pages'][pi]['cid']) + "&aid=" + str(aid) + "&bvid=" +initial_state['videoData']["bvid"]+"&buvid=FB2BB46F-B1F3-4BDA-A589-33348940411A155830infoc" + print("lrc url", lrcurl) + # -H 'Referer: https://www.bilibili.com/video/BV1zE411T7nb' + h = dict() + jsonOfLrc = get_content(lrcurl, headers={"Referer": "https://www.bilibili.com/video/" + initial_state['videoData']["bvid"]}) + # Example line: + # {"allow_submit":false,"lan":"","lan_doc":"","subtitles":[{"id":23916631605379079,"lan":"zh-CN","lan_doc":"中文（中国）","is_lock":false,"subtitle_url":"//i0.hdslb.com/bfs/subtitle/dfb81041cf92b5c2ebce2540cd14c9e49674f460.json"}]} + subtitleMeta = match1(jsonOfLrc, r'(.*?)') + subtitlejson = json.loads(subtitleMeta) + print(subtitlejson) + if len(subtitlejson["subtitles"])> 0: + suburl = subtitlejson["subtitles"][0]["subtitle_url"] + subjson = get_content("https:" + suburl) + file = '' + datas = json.loads(subjson) + i = 1 + for data in datas['body']: + start = data['from'] # 获取开始时间 + stop = data['to'] # 获取结束时间 + content = data['content'] # 获取字幕内容 + file += '{}\n'.format(i) # 加入序号 + hour = math.floor(start) // 3600 + minute = (math.floor(start) - hour * 3600) // 60 + sec = math.floor(start) - hour * 3600 - minute * 60 + minisec = int(math.modf(start)[0] * 100) # 处理开始时间 + file += str(hour).zfill(2) + ':' + str(minute).zfill(2) + ':' + str(sec).zfill(2) + ',' + str(minisec).zfill(2) # 将数字填充0并按照格式写入 + file += ' --> ' + hour = math.floor(stop) // 3600 + minute = (math.floor(stop) - hour * 3600) // 60 + sec = math.floor(stop) - hour * 3600 - minute * 60 + minisec = abs(int(math.modf(stop)[0] * 100 - 1)) # 此处减1是为了防止两个字幕同时出现 + file += str(hour).zfill(2) + ':' + str(minute).zfill(2) + ':' + str(sec).zfill(2) + ',' + str(minisec).zfill(2) + file += '\n' + content + '\n\n' # 加入字幕文字 + i += 1 + srtfilename = '%s.srt' % get_filename(tttt) + with open(os.path.join(".", srtfilename), 'w', encoding='utf-8') as f: + f.write(file) # 将数据写入文件 + # purl = 'https://www.bilibili.com/video/av%s?p=%s' % (aid, pi+1) # self.__class__().download_by_url(purl, **kwargs) diff --git a/src/you_get/util/fs.py b/src/you_get/util/fs.py index c04a10a74d..3ecd20e6e7 100644 --- a/src/you_get/util/fs.py +++ b/src/you_get/util/fs.py @@ -43,5 +43,5 @@ def legitimize(text, os=detect_os()): if text.startswith("."): text = text[1:] - text = text[:80] # Trim to 82 Unicode characters long + text = text[:160] # Trim to 82 Unicode characters long return text From abd65c3c1479bbdcc280c198a852af0e4dd937ad Mon Sep 17 00:00:00 2001 From: ed Date: Tue, 3 Sep 2024 09:44:30 +0800 Subject: [PATCH 2/2] bilibili download support --- src/you_get/extractors/bilibili.py | 30 +++++++++++++++--------------- 1 file changed, 15 insertions(+), 15 deletions(-) diff --git a/src/you_get/extractors/bilibili.py b/src/you_get/extractors/bilibili.py index fb5444471d..8d694275be 100644 --- a/src/you_get/extractors/bilibili.py +++ b/src/you_get/extractors/bilibili.py @@ -1,4 +1,6 @@ #!/usr/bin/env python +import json +import re from ..common import * from ..extractor import VideoExtractor @@ -339,21 +341,15 @@ def prepare(self, **kwargs): # bangumi elif sort == 'bangumi': - initial_state_text = match1(html_content, r'__INITIAL_STATE__=(.*?);\(function\(\)') # FIXME - initial_state = json.loads(initial_state_text) - - # warn if this bangumi has more than 1 video - epn = len(initial_state['epList']) - if epn > 1 and not kwargs.get('playlist'): - log.w('This bangumi currently has %s videos. (use --playlist to download all videos.)' % epn) + eposide = kwargs['eposide_data'] # set video title - self.title = initial_state['h1Title'] + self.title = eposide['long_title'] # construct playinfos - ep_id = initial_state['epInfo']['id'] - avid = initial_state['epInfo']['aid'] - cid = initial_state['epInfo']['cid'] + ep_id = eposide['ep_id'] + avid = eposide['aid'] + cid = eposide['cid'] playinfos = [] api_url = self.bilibili_bangumi_api(avid, cid, ep_id) api_content = get_content(api_url, headers=self.bilibili_headers(referer=self.url)) @@ -717,13 +713,17 @@ def download_playlist_by_url(self, url, **kwargs): self.download(**kwargs) elif sort == 'bangumi': - initial_state_text = match1(html_content, r'__INITIAL_STATE__=(.*?);\(function\(\)') # FIXME - initial_state = json.loads(initial_state_text) - epn, i = len(initial_state['epList']), 0 - for ep in initial_state['epList']: + epId = re.search(r'"videoId":"ep(.*?)"', html_content).group(1) + eposide_content = get_content(url="https://api.bilibili.com/pgc/view/web/ep/list?ep_id=%s" % (epId), + headers=self.bilibili_headers(referer=self.url)) + eposide_json = json.loads(eposide_content)["result"]["episodes"] + epn, i = len(eposide_json), 0 + for ep in eposide_json: i += 1; log.w('Extracting %s of %s videos ...' % (i, epn)) ep_id = ep['id'] epurl = 'https://www.bilibili.com/bangumi/play/ep%s/' % ep_id + kwargs['eposide_data'] = ep + ep['long_title']= ("%02d" % i) + ep['long_title'] self.__class__().download_by_url(epurl, **kwargs) elif sort == 'bangumi_md':