import requests
import execjs

pageSize = int(input('pageSize(不要大于100):'))
pageIndex = int(input('pageIndex（尽量小点）:'))
# 获取到申请头网址的html页面数据
url = 'https://www.baiten.cn/results/l/java/.html?type=l'
headers = {
    'Content-Type':'application/x-www-form-urlencoded',
    'charset':'UTF-8',
    'Host':'www.baiten.cn',
    'Referer':'https://www.baiten.cn/results/l/java/.html?type=l',
    'Cookie':'UM_distinctid=17cee04232917-0ce7616d753d2c-57b1a33-144000-17cee04232a152; BSESSION=ebd591955fd30d1257027dbb9963df56f77fa57e2713e5a3; CNZZDATA1275904268=820333148-1636079972-|1637373846; JSESSIONID=2CEB334BD9F1C7AB209ABCC0E1FCD9B6; Hm_lvt_7fc44f078bf7b5e19489428c362109a3=1637371390,1637376101,1637380097,1637380316; PD=ef38206be5b44e431a74453174c7df9bf2477939ae99f267254b09e8136946e9bd45a801cd1d3486; yunsuo_session_verify=58a343a92e57e07624bb552dd150650c; Hm_lpvt_7fc44f078bf7b5e19489428c362109a3=1637382574',
    'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/95.0.4638.69 Safari/537.36',
    'X-Requested-With':'XMLHttpRequest'
}
response = requests.get(url=url, headers=headers).text
str = response
# 获取到被加密的数据token
token = ''
for i in range(5568, 5648):
    token = token + str[i]

# 利用execjs模块对获取到的token进行加密
ctx1 = execjs.compile("""
var keyStr = "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/=";
function encode64(input) {
    var output = "";
    var chr1, chr2, chr3 = "";
    var enc1, enc2, enc3, enc4 = "";
    var i = 0;
    do {
        chr1 = input.charCodeAt(i++);
        chr2 = input.charCodeAt(i++);
        chr3 = input.charCodeAt(i++);
        enc1 = chr1 >> 2;
        enc2 = ((chr1 & 3) << 4) | (chr2 >> 4);
        enc3 = ((chr2 & 15) << 2) | (chr3 >> 6);
        enc4 = chr3 & 63;
        if (isNaN(chr2)) {
            enc3 = enc4 = 64
        } else {
            if (isNaN(chr3)) {
                enc4 = 64
            }
        }
        output = output + keyStr.charAt(enc1) + keyStr.charAt(enc2) + keyStr.charAt(enc3) + keyStr.charAt(enc4);
        chr1 = chr2 = chr3 = "";
        enc1 = enc2 = enc3 = enc4 = ""
    } while (i < input.length);
    return output;
}
""")
ctx1.call("encode64", token)
# 获取加密网站https://www.baiten.cn/results/list/token
url1 = ''
str1 = 'https://www.baiten.cn/results/list/'
str2 = ctx1.call("encode64", token)
url1 = url1 + str1 + str2

# 爬取到被加密的网站上专利的数据
url2 = url1
data = {
    'sc':'',
    'q':'java',
    'sort':'',
    'sortField':'',
    'fq':'',
    'pageSize':pageSize,
    'pageIndex':pageIndex,
    'type':'l',
    'merge':'no-merge'
}
headers = {
    'Content-Length':'79',
    'Content-Type':'application/x-www-form-urlencoded',
    'charset':'UTF-8',
    'Host':'www.baiten.cn',
    'Origin':'https://www.baiten.cn',
    'Referer':'https://www.baiten.cn/results/l/java/.html?type=l',
    'Cookie':'UM_distinctid=17cee04232917-0ce7616d753d2c-57b1a33-144000-17cee04232a152; BSESSION=ebd591955fd30d1257027dbb9963df56f77fa57e2713e5a3; CNZZDATA1275904268=820333148-1636079972-|1637373846; JSESSIONID=2CEB334BD9F1C7AB209ABCC0E1FCD9B6; Hm_lvt_7fc44f078bf7b5e19489428c362109a3=1637371390,1637376101,1637380097,1637380316; PD=ef38206be5b44e431a74453174c7df9bf2477939ae99f267254b09e8136946e9bd45a801cd1d3486; yunsuo_session_verify=58a343a92e57e07624bb552dd150650c; Hm_lpvt_7fc44f078bf7b5e19489428c362109a3=1637383707',
    'sec-ch-ua-mobile':'?0',
    'sec-ch-ua-platform':'Windows',
    'Sec-Fetch-Dest':'empty',
    'Sec-Fetch-Mode':'cors',
    'Sec-Fetch-Site':'same-origin',
    'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/95.0.4638.69 Safari/537.36',
    'X-Requested-With':'XMLHttpRequest'
}
requests1 = requests.post(url2, headers=headers, data=data).json()
result = requests1['cubePatentSearchResponse']['documents']
patentdata = open('data.txt', 'w+')
i = 0
while i < pageSize:
    result = requests1['cubePatentSearchResponse']['documents'][i]['field_values']
    ti = result['ti']                       # 专利名称
    id = result['id']                       # 申请号
    pn = result['pn']                       # 公开号
    pa = result['pa']                       # 申请（专利权）人是个列表
    str_pa = ''
    for m1 in pa:
        str_pa = str_pa + '  ' + m1
    In = result['in']                       # 发明人是个列表
    str_in = ''
    for m2 in pa:
        str_in = str_in + '  ' + m2
    ad = result['ad']                       # 申请日
    pd = result['pd']                       # 公开日
    ic1 = result['ic1']                    # 主分类号
    aic1 = result['aic1']                   # 分类号
    aa = result['aa']                       # 地址
    co = result['co']                       # 国省代码
    kw = result['kw']                       # 技术关键词
    str_kw = ''
    for m3 in kw:
        str_kw = str_kw + '  ' + m3
    ls1 = result['ls1']                     # 专利授权情况
    ab = result['ab']                       # 摘要
    ac = result['ac']                       # 学术搜索
    num = i+1
    patentdata.write('第')
    patentdata.write('%d' %pageIndex)
    patentdata.write('页的专利产品' + '\n')
    patentdata.write('第')
    patentdata.write('%d' %num)
    patentdata.write('个专利产品' + '\n')
    patentdata.write('专利名称:' + ti + '\n')
    patentdata.write('申请号:' + id + '\n')
    patentdata.write('公开号:' + pn + '\n')
    patentdata.write('申请（专利权）人:' + str_pa + '\n')
    patentdata.write('发明人:' + str_in + '\n')
    patentdata.write('申请日:' + ad + '\n')
    patentdata.write('公开日:' + pd + '\n')
    patentdata.write('主分类号:' + ic1 + '\n')
    patentdata.write('分类号:' + aic1 + '\n')
    patentdata.write('地址:' + aa + '\n')
    patentdata.write('国省代码:' + co + '\n')
    patentdata.write('技术关键词:' + str_kw + '\n')
    patentdata.write('专利授权情况:' + ls1 + '\n')
    patentdata.write('摘要:' + ab + '\n')
    patentdata.write('学术搜索:' + ac + '\n')
    i += 1

else:
    print("数据获取完毕！")