Biligrab 0.1

Biligrab01.py

'''
Biligrab 0.1
Beining@ACICFG
http://www.cnbeining.com/
A most simple tool to download comments from Bilibili.
Require: Python 2.7
Usage:
python Biligrab01.py
>>>av12450
>>>p1
Simple as it goes.
'''
import sys
import os
from StringIO import StringIO
import gzip
import urllib2
import sys



#----------------------------------------------------------------------
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))
            if 'partname' in lines:
                partname = lines[12:-11]
                print('partname is ' + str(partname))
            if 'title' in lines:
                title = lines[9:-8]
                print('title is ' + str(title))
    except:  #If API failed
        print('ERROR: Cannot connect to API server!')


def main(vid, p):
    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'+vid+'/index_'+p+'.html'
    print('Fetching webpage...')
    request = urllib2.Request(biliurl)
    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
    if cid is 0:
        print('Cannot find cid, trying to do it brutely...')
        print('Fetching webpage...')
        request = urllib2.Request(videourl)
        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
    '''
    if cid is 0:
        vid = int(int(vid) - 1)
        p = 1
        find_cid_api(vid-1, p)
        cid = str(int(cid) + 1)
        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...')
        request = urllib2.Request(biliurl)
        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))
            if 'partname' in lines:
                partname = lines[12:-11]
                print('partname is ' + str(partname))
            if 'title' in lines:
                title = lines[9:-8]
                print('title is ' + str(title))
    '''
    if cid is 0:
        cid = str(raw_input('Input the cid by yourself!'))
    if cid is '':
        exit()
    #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
    print('Fetching XML...')
    os.system('curl -o "'+filename+'.xml" --compressed  http://comment.bilibili.tv/'+cid+'.xml')
    #os.system('gzip -d '+cid+'.xml.gz')
    print('The XML file, ' + filename + '.xml should be ready...enjoy!')
    exit()

vid = str(input('av'))
p = str(input('P'))
main(vid, p)