Biligrab 0.64:还是Hotfix,解决批量下载文件夹嵌套问题

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。
gist.github.com/superwbd/9605757

'''
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 thoughts on “Biligrab 0.64:还是Hotfix,解决批量下载文件夹嵌套问题

  1. akw28888

    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

    Reply
    1. Beining Post author

      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。。。

      Reply
    1. Beining Post author

      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。

      Reply

Leave a Reply to Beining Cancel reply

Your email address will not be published. Required fields are marked *