蛋疼啊。
啥也不说了。
今天B站阿姆斯特丹机器貌似故障，喜大普奔啊。
代码藏起来了。
https://gist.github.com/superwbd/9605757
|
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 |
''' Biligrab 0.64 Beining@ACICFG cnbeining[at]gmail.com http://www.cnbeining.com MIT licence ''' import sys import os from StringIO import StringIO import gzip import urllib2 import sys import commands from xml.dom.minidom import parse, parseString import xml.dom.minidom reload(sys) sys.setdefaultencoding('utf-8') global vid global cid global partname global title global videourl global part_now def list_del_repeat(list): """delete repeating items in a list, and keep the order. http://www.cnblogs.com/infim/archive/2011/03/10/1979615.html""" l2 = [] [l2.append(i) for i in list if not i in l2] return(l2) #---------------------------------------------------------------------- def find_cid_api(vid, p): """find cid and print video detail""" global cid global partname global title global videourl cid = 0 title = '' partname = '' biliurl = 'http://api.bilibili.tv/view?type=xml&appkey=876fe0ebd0e67a0f&id=' + str(vid) + '&page=' + str(p) videourl = 'http://www.bilibili.tv/video/av'+ str(vid)+'/index_'+ str(p)+'.html' print('Fetching webpage...') try: request = urllib2.Request(biliurl, headers={ 'User-Agent' : 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_9_0) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/31.0.1650.63 Safari/537.36', 'Cache-Control': 'no-cache', 'Pragma': 'no-cache' }) response = urllib2.urlopen(request) data = response.read() data_list = data.split('\n') for lines in data_list: if 'cid' in lines: cid = lines[7:-6] print('cid is ' + str(cid)) break for lines in data_list: if 'partname' in lines: partname = lines[12:-11] print('partname is ' + str(partname)) break for lines in data_list: if 'title' in lines: title = lines[9:-8] print('title is ' + str(title)) break except: #If API failed print('ERROR: Cannot connect to API server!') #---------------------------------------------------------------------- def find_cid_flvcd(videourl): """""" global vid global cid global partname global title print('Fetching webpage via Flvcd...') request = urllib2.Request(videourl, headers={ 'User-Agent' : 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_9_0) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/31.0.1650.63 Safari/537.36', 'Cache-Control': 'no-cache', 'Pragma': 'no-cache' }) request.add_header('Accept-encoding', 'gzip') response = urllib2.urlopen(request) if response.info().get('Content-Encoding') == 'gzip': buf = StringIO( response.read()) f = gzip.GzipFile(fileobj=buf) data = f.read() data_list = data.split('\n') #Todo: read title for lines in data_list: if 'cid=' in lines: cid = lines.split('&') cid = cid[0].split('=') cid = cid[-1] print('cid is ' + str(cid)) break #---------------------------------------------------------------------- def main(vid, p, oversea): global cid global partname global title global videourl global is_first_run biliurl = 'http://api.bilibili.tv/view?type=xml&appkey=876fe0ebd0e67a0f&id=' + str(vid) + '&page=' + str(p) videourl = 'http://www.bilibili.tv/video/av'+ str(vid)+'/index_'+ str(p)+'.html' output = commands.getstatusoutput('ffmpeg --help') if str(output[0]) == '32512': print('FFmpeg does not exist! Trying to get you a binary, need root...') os.system('sudo curl -o /usr/bin/ffmpeg https://raw.githubusercontent.com/superwbd/ABPlayerHTML5-Py--nix/master/ffmpeg') output = commands.getstatusoutput('aria2c --help') if str(output[0]) == '32512': print('aria2c does not exist! Trying to get you a binary, need root... Thanks for @MartianZ \'s work.') os.system('sudo curl -o /usr/bin/aria2c https://raw.githubusercontent.com/MartianZ/fakeThunder/master/fakeThunder/aria2c') find_cid_api(vid, p) global cid if cid is 0: print('Cannot find cid, trying to do it brutely...') find_cid_flvcd(videourl) if cid is 0: is_black3 = str(raw_input('Strange, still cannot find cid... Type y for trying the unpredictable way, or input the cid by yourself, press ENTER to quit.')) if 'y' in str(is_black3): vid = vid - 1 p = 1 find_cid_api(vid-1, p) cid = cid + 1 elif str(is_black3) is '': print('Cannot get cid anyway! Quit.') exit() else: cid = str(is_black3) #start to make folders... if title is not '': folder = title else: folder = cid if partname is not '': filename = partname elif title is not '': filename = title else: filename = cid # In case make too much folders folder_to_make = os.getcwd() + '/' + folder if is_first_run == 0: if not os.path.exists(folder_to_make): os.makedirs(folder_to_make) is_first_run = 1 os.chdir(folder_to_make) print('Fetching XML...') os.system('curl -o "'+filename+'.xml" --compressed http://comment.bilibili.cn/'+cid+'.xml') #os.system('gzip -d '+cid+'.xml.gz') print('The XML file, ' + filename + '.xml should be ready...enjoy!') print('Finding video location...') #try api if oversea == '1': try: request = urllib2.Request('http://interface.bilibili.cn/v_cdn_play?cid='+cid, headers={ 'User-Agent' : 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_9_0) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/31.0.1650.63 Safari/537.36', 'Cache-Control': 'no-cache', 'Pragma': 'no-cache' }) except: print('ERROR: Cannot connect to API server!') else: try: request = urllib2.Request('http://interface.bilibili.tv/playurl?cid='+cid, headers={ 'User-Agent' : 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_9_0) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/31.0.1650.63 Safari/537.36', 'Cache-Control': 'no-cache', 'Pragma': 'no-cache' }) except: print('ERROR: Cannot connect to API server!') response = urllib2.urlopen(request) data = response.read() #print(data_list) rawurl = [] dom = parseString(data) for node in dom.getElementsByTagName('url'): if node.parentNode.tagName == "durl": rawurl.append(node.toxml()[14:-9]) #print(str(node.toxml()[14:-9])) pass if rawurl is []: #hope this never happen request = urllib2.Request('http://www.flvcd.com/parse.php?kw='+videourl, headers={ 'User-Agent' : 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_9_0) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/31.0.1650.63 Safari/537.36', 'Cache-Control': 'no-cache', 'Pragma': 'no-cache' }) request.add_header('Accept-encoding', 'gzip') response = urllib2.urlopen(request) data = response.read() data_list = data.split('\n') for items in data_list: if 'name' in items and 'inf' in items and 'input' in items: c = items rawurl = c[39:-5] rawurl = rawurl.split('|') break #print(rawurl) vid_num = len(rawurl) #print(rawurl) print(str(vid_num) + ' videos in part ' + str(part_now) + ' to download, fetch yourself a cup of coffee...') for i in range(vid_num): print('Downloading ' + str(i+1) + ' of ' + str(vid_num) + ' videos in part ' + str(part_now) + '...') #print('aria2c -llog.txt -c -s16 -x16 -k1M --out '+str(i)+'.flv "'+rawurl[i]+'"') os.system('aria2c -larialog.txt -c -s16 -x16 -k1M --out '+str(i)+'.flv "'+rawurl[i]+'"') #os.system('aria2c -larialog.txt -c -s16 -x16 -k1M --out '+str(i)+'.flv "'+rawurl[i]+'"') #not debugging, not fun. f = open('ff.txt', 'w') ff = '' os.getcwd() for i in range(vid_num): ff = ff + 'file \'' + str(os.getcwd()) + '/'+ str(i) + '.flv\'\n' ff = ff.encode("utf8") f.write(ff) f.close() print('Concating videos...') os.system('ffmpeg -f concat -i ff.txt -c copy "'+filename+'".mp4') os.system('rm -r ff.txt') for i in range(vid_num): os.system('rm -r '+str(i)+'.flv') print('Done, enjoy yourself!') # vid = str(raw_input('av')) p_raw = str(raw_input('P')) oversea = str(input('Oversea?')) p_list = [] p_raw = p_raw.split(',') for item in p_raw: if '~' in item: #print(item) lower = 0 higher = 0 item = item.split('~') try: lower = int(item[0]) except: print('Cannot read lower!') try: higher = int(item[1]) except: print('Cannot read higher!') if lower == 0 or higher == 0: if lower == 0 and higher != 0: lower = higher elif lower != 0 and higher == 0: higher = lower else: print('Cannot find any higher or lower, ignoring...') #break mid = 0 if higher < lower: mid = higher higher = lower lower = mid p_list.append(lower) while lower < higher: lower = lower + 1 p_list.append(lower) #break else: try: p_list.append(int(item)) except: print('Cannot read "'+str(item)+'", abondon it.') #break p_list = list_del_repeat(p_list) global is_first_run is_first_run = 0 part_now = '0' print(p_list) for p in p_list: part_now = str(p) main(vid, p, oversea) exit() ''' data_list = data.split('\r') for lines in data_list: lines = str(lines) if '<url>' in lines: if 'youku' in lines: url = lines[17:-9] elif 'sina' in lines: url = lines[16:-9] elif 'qq.com' in lines: url = lines[17:-9] elif 'letv.com' in lines: url = lines[17:-9] break elif 'acgvideo' in lines: url = lines[17:-9] is_local = 1 rawurl.append(url) if 'backup_url' in lines and is_local is 1: break''' |
4 comments
Skip to comment form ↓
akw28888
2014 年 5 月 9 日 在 上午 11:05 (UTC -5) Link to this comment
說起來渣浪扣掉自家8080的服務器 其他視頻應該都有全球CDN的吧…………不過我這裡有的會解析台灣的node給我 有的卻解析回china的
Beining
2014 年 5 月 12 日 在 上午 12:20 (UTC -5) Link to this comment
8080服务器昙花一现。我不知道这些服务器来源是啥 为什么竟然不使用蓝汛的CDN。
不同的node应该是因为没有缓存吧。我在LA有时候也会解析广东的节点。。。
nuomi
2014 年 5 月 11 日 在 上午 5:29 (UTC -5) Link to this comment
没找到地方，这里算了。
——————————
http://m13253.blogspot.com/2013/10/ways-to-join-videos-losslessly.html
“方法二：FFmpeg concat 分离器”，无需 TS 中转，未测试。
Beining
2014 年 5 月 12 日 在 上午 12:19 (UTC -5) Link to this comment
我用的就是这个方法。
细看下面，我建立了一个ff.txt。里面是一个个的视频。这里我就准备直接concat了。
这是最好用的办法。