pypy

#coding:utf-8

import requests,codecs
import json
import re
import os, shutil
import urllib.request, urllib.error
from requests.cookies import RequestsCookieJar
import time
from PyPDF2 import PdfFileReader, PdfFileWriter, PdfFileMerger
import urllib3
import hashlib

class calcSig(object):
    key1 = ‘57218436‘
    key2 = ‘15387264‘
    rstr = ‘efc84c17‘

    def shuffle(self, p1, p2):
        p = ‘‘
        p += p1[int(p2[0], 10) - 1]
        p += p1[int(p2[1], 10) - 1]
        p += p1[int(p2[2], 10) - 1]
        p += p1[int(p2[3], 10) - 1]
        p += p1[int(p2[4], 10) - 1]
        p += p1[int(p2[5], 10) - 1]
        p += p1[int(p2[6], 10) - 1]
        p += p1[int(p2[7], 10) - 1]
        return p.lower()

    # 生成 as和cp字段
    def ppp(self, u_md5, u_key1, u_key2):
        ascp = [0] * 36
        ascp[0] = ‘a‘
        ascp[1] = ‘1‘
        for i in range(0, 8):
            ascp[2 * (i + 1)] = u_md5[i]
            ascp[2 * i + 3] = u_key2[i]
            ascp[2 * i + 18] = u_key1[i]
            ascp[2 * i + 1 + 18] = u_md5[i + 24]
        ascp[-2] = ‘e‘
        ascp[-1] = ‘1‘

        return ‘‘.join(ascp)

    # 解析url参数
    def parseURL(self, url):
        param_index = url.find(‘?‘)
        param = url[param_index + 1:]
        param_list = param.split(‘&‘)
        param_list.append(‘rstr=‘+self.rstr)
        param_list = sorted(param_list)
        result = ‘‘
        for a in param_list:
            tmp = a.split(‘=‘)
            tmp[1] = tmp[1].replace(‘+‘, ‘a‘)
            tmp[1] = tmp[1].replace(‘ ‘, ‘a‘)
            result += tmp[1]
        return result

    # 计算md5
    def calcMD5(self, str_encode):
        m = hashlib.md5()
        m.update(str_encode.encode(‘utf-8‘))
        return m.hexdigest()

    def work(self, url, curtime):
        url_param = self.parseURL(url)
        p_md5 = self.calcMD5(url_param)
        if curtime & 1:
            p_md5 = self.calcMD5(p_md5)
        hexTime = hex(curtime)[2:]
        aa = self.shuffle(hexTime, self.key1)
        bb = self.shuffle(hexTime, self.key2)
        sig = self.ppp(p_md5, aa, bb)
        return (‘%s&as=%s&cp=%s‘ % (url, sig[:18], sig[18:]))
        # return (sig[:18], sig[18:])



def getVideo_requests(url,video_Name):
    print(‘>>> 开始下载 ！ \n‘)
    mname=‘%d_%s‘ % (time.time(), mid)
    tempName_video = os.path.join(DOWNLOAD_PATH,‘%s.pdf‘%mname)  # 创建临时文件
    try:
        #cookie_jar = RequestsCookieJar()
        c = requests.cookies.RequestsCookieJar()
        s = requests.Session()
        c.set("JSESSIONID", "94E22BF178A02E950FABC28678D0AABA", domain="eresource.library.sh.cn",path="/")
        c.set("JSESSIONID", "A4FD3CC5DD934282AA003EC932399FB7", domain="eresource.library.sh.cn",path=‘/objserver/‘)
        s.cookies.update(c)
        response = requests.get(url=url, timeout=120,cookies=c,headers=headers,verify=False)
        print(url)
        with open(tempName_video, ‘wb‘) as f:
            f.write(response.content)
            f.close()
    except Exception as e:
        print(e)    
    print(‘>>> %s.pdf 下载完成! ‘%mid)
    if nowpage==205:
        mergefiles(DOWNLOAD_PATH,‘out.pdf‘)
    


def getfilenames(filepath=‘‘,filelist_out=[],file_ext=‘all‘):
    # 遍历filepath下的所有文件，包括子目录下的文件
    for fpath, dirs, fs in os.walk(filepath):
        for f in fs:
            fi_d = os.path.join(fpath, f)
            if  file_ext == ‘all‘:
                filelist_out.append(fi_d)
            elif os.path.splitext(fi_d)[1] == file_ext:
                filelist_out.append(fi_d)
            else:
                pass
    return filelist_out
    
def mergefiles(path, output_filename, import_bookmarks=False):
    # 遍历目录下的所有pdf将其合并输出到一个pdf文件中，输出的pdf文件默认带书签，书签名为之前的文件名
    # 默认情况下原始文件的书签不会导入，使用import_bookmarks=True可以将原文件所带的书签也导入到输出的pdf文件中
    merger = PdfFileMerger()
    filelist = getfilenames(filepath=path, file_ext=‘.pdf‘)
    print(filelist)
    if len(filelist) == 0:
        print("当前目录及子目录下不存在pdf文件")
        sys.exit()
    for filename in filelist:
        f = codecs.open(filename, ‘rb‘)
        file_rd = PdfFileReader(f)
        short_filename = os.path.basename(os.path.splitext(filename)[0])
        if file_rd.isEncrypted == True:
            print(‘不支持的加密文件：%s‘%(filename))
            continue
        merger.append(file_rd, bookmark=short_filename, import_bookmarks=import_bookmarks)
        print(‘合并文件：%s‘%(filename))
        f.close()
    out_filename=os.path.join(os.path.abspath(path), output_filename)
    merger.write(out_filename)
    print(‘合并后的输出文件：%s‘%(out_filename))
    merger.close()

def jsppost(url,data):
    print(‘>>> jsp开始 ！ \n‘)
    try:
        #cookie_jar = RequestsCookieJar()
        #c = requests.cookies.RequestsCookieJar()
        #s = requests.Session()
        #c.set("JSESSIONID", "94E22BF178A02E950FABC28678D0AABA", domain="eresource.library.sh.cn",path="/")
        #c.set("JSESSIONID", "A4FD3CC5DD934282AA003EC932399FB7", domain="eresource.library.sh.cn",path=‘/objserver/‘)
        #s.cookies.update(c)
        response = requests.post(url=url,data=data, timeout=120,cookies=c,headers=headers,verify=False)
        
    except Exception as e:
        print(e)

def jsp(url):
    print(‘>>> jsp开始 ！ \n‘)
    try:
        #cookie_jar = RequestsCookieJar()
        c = requests.cookies.RequestsCookieJar()
        s = requests.Session()
        c.set("JSESSIONID", "94E22BF178A02E950FABC28678D0AABA", domain="eresource.library.sh.cn",path="/")
        c.set("JSESSIONID", "A4FD3CC5DD934282AA003EC932399FB7", domain="eresource.library.sh.cn",path=‘/objserver/‘)
        s.cookies.update(c)
        #response = requests.get(url=url, timeout=120,cookies=c,headers=headers,verify=False)
        r = requests.get(url=url, timeout=120,headers=headers,verify=False)
        tt=json.loads(r.text).get(‘min_time‘)
        print(tt)
        #print(json.loads(r.text).get(‘followers‘))
        file = r‘mdata.txt‘
        with open(file,‘a+‘,encoding=‘utf-8‘) as f:
            f.write(str(json.loads(r.text).get(‘followers‘))+‘,‘)
        time.sleep(20)
        getFollower(str(tt))
    except Exception as e:
        print(e)        

def run(start_url):
    video_Name = "myvideo"
    getVideo_requests(start_url,video_Name)

def getFollower(max_time):
    t = time.time()
    user_id=‘127178283690750‘
    ts=int(t)                #秒级时间戳
    _rticket=str(int(round(t * 1000)))
    c = calcSig()
    url = "https://aweme.snssdk.com/aweme/v1/user/follower/list/?user_id="+user_id+"&max_time="+max_time+"&_rticket="+_rticket+"&ts="+str(ts)+"&count=20&retry_type=no_retry&iid=82879820134&device_id=69189073301&ac=wifi&channel=360_new&aid=1128&app_name=aweme&version_code=168&version_name=1.6.8&device_platform=android&ssmix=a&device_type=Redmi+4A&device_brand=Xiaomi&language=zh&os_api=23&os_version=6.0.1&openudid=29f385a1e0b60ece&manifest_version_code=210&resolution=720*1280&dpi=320&update_version_code=2102"
    murl=c.work(url,ts)
    print(c.work(url,ts))
    jsp(murl)

if __name__ == "__main__":
    print("加载中....")
    DOWNLOAD_PATH = r‘E:\\python\\pdf\\‘  #下载目录
    urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning)
    #mergefiles(DOWNLOAD_PATH,‘out.pdf‘)
    """
    headers = {"User-Agent":"Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/76.0.3809.100 Safari/537.36","Referer": "http://wrd2016.library.sh.cn/channel/stjp/?tdsourcetag=s_pcqq_aiomsg"}
    
    requests.packages.urllib3.disable_warnings()
    jsp(‘http://eresource.library.sh.cn:8080/objserver/jsp/browserjp.jsp‘)
    time.sleep(0.1)
    
    headers = {"User-Agent":"Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/76.0.3809.100 Safari/537.36","Referer": "http://eresource.library.sh.cn:8080/objserver/jsp/browserjp.jsp"}
    jsp(‘http://eresource.library.sh.cn:8080/objserver/jsp/fcjp.jsp‘)
    time.sleep(0.1)
    
    headers = {"User-Agent":"Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/76.0.3809.100 Safari/537.36","Referer": "http://eresource.library.sh.cn:8080/objserver/jsp/browserjp.jsp"}
    jsp(‘http://eresource.library.sh.cn:8080/objserver/jsp/sy.jsp‘)
    time.sleep(0.1)
    
    headers = {"User-Agent":"Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/76.0.3809.100 Safari/537.36","Referer": "http://eresource.library.sh.cn:8080/objserver/jsp/browserjp.jsp"}
    jsp(‘http://eresource.library.sh.cn:8080/objserver/jsp/fy.jsp‘)
    time.sleep(0.1)
        
    fo = open(‘E:\python\pdf\merged_pdf_file.pdf‘, "wb")
    print("文件名为: ", fo.name)
    fo.close()
    """
    #"""
    for i in range(1):
        #headers = {"Accept":"","Accept-Encoding":"gzip","User-Agent":"com.ss.android.ugc.aweme/750 (Linux; U; Android 6.0.1; zh_CN; Redmi 4A; Build/MMB29M; Cronet/58.0.2991.0)","Cookie": "install_id=82603796791; ttreq=1$1cd2da467f7f9f07d5de1aa593622dc8e06a7c93; odin_tt=cbe4c5411d373bcc1c3d572c33fbd7cd291508f9058b0c999dd5a432c031db5692d05ebc521e96dfce5ebb02201f1934a7bb907f7d37d6a30f308f580d97c3da; qh[360]=1","sdk-version":"1","X-Gorgon":"030428800001f0e89460d16043016864424adf199af7a8b2e148","X-Khronos":"1565712299","X-SS-REQ-TICKET":"1565712299115"}
        #headers = {"User-Agent":"com.ss.android.ugc.aweme/750 (Linux; U; Android 6.0.1; zh_CN; Redmi 4A; Build/MMB29M; Cronet/58.0.2991.0)","Cookie": "install_id=82603796791; ttreq=1$1cd2da467f7f9f07d5de1aa593622dc8e06a7c93; odin_tt=cbe4c5411d373bcc1c3d572c33fbd7cd291508f9058b0c999dd5a432c031db5692d05ebc521e96dfce5ebb02201f1934a7bb907f7d37d6a30f308f580d97c3da; qh[360]=1","sdk-version":"1","X-Gorgon":"03e0906d00016fa814d014d60446c7c71713b86fe930f83d8ff5","X-Khronos":"1565778310","X-SS-REQ-TICKET":"1565777837303"}
        headers = {"User-Agent":"com.ss.android.ugc.aweme/750 (Linux; U; Android 6.0.1; zh_CN; Redmi 4A; Build/MMB29M; Cronet/58.0.2991.0)","Cookie": "install_id=82879820134; ttreq=1$737084fed40b6240b948d2e5f0895b8df4af9e2f; odin_tt=8c2caed1fe142cfbbdf2a4b5e3fa397d62dbcd9137cc328c4631dfa0c18120d7cb5797df33708d164e7423e4913134028431d801ee758ebef1c15954d9ca470f; qh[360]=1"}
        #jsp("https://aweme.snssdk.com/aweme/v1/user/follower/list/?user_id=80954225804&max_time=1565784692&count=20&retry_type=no_retry&mcc_mnc=&iid=82715258125&device_id=69189073301&ac=wifi&channel=360_new&aid=1128&app_name=aweme&version_code=380&version_name=1.8.0&device_platform=android&ssmix=a&device_type=Redmi+4A&device_brand=Xiaomi&language=zh&os_api=23&os_version=6.0.1&openudid=29f385a1e0b60ece&manifest_version_code=380&resolution=720*1280&dpi=320&update_version_code=3802&_rticket=1565784692555&js_sdk_version=1.6.4&mas=0180c7997d71bdad7fd997615978f4f1c98c8c1c4ccc46868c26ec")
        #jsp("https://aweme.snssdk.com/aweme/v1/user/follower/list/?user_id=127178283690750&max_time=1565919239&count=20&retry_type=no_retry&iid=82803867752&device_id=38693548692&ac=wifi&channel=360_new&aid=1128&app_name=aweme&version_code=168&version_name=1.6.8&device_platform=android&ssmix=a&device_type=M5+Note&device_brand=Meizu&language=zh&os_api=24&os_version=7.0&uuid=865066037588709&openudid=797cadbbed256853&manifest_version_code=210&resolution=1080*1920&dpi=480&update_version_code=2102&_rticket=1565919256352&ts=1565919256&as=a1a5d0056821ed2806&cp=0818d75184625587e1")
        time.sleep(0.2)
        t = time.time()
        user_id=‘103184660180‘
        ts=int(t)                #秒级时间戳
        max_time=‘1565925565‘#str(ts)
        _rticket=str(int(round(t * 1000)))
        c = calcSig()
        #https://aweme.snssdk.com/aweme/v1/user/follower/list/?user_id=103184660180&max_time=1565923611&count=20&retry_type=no_retry&iid=82879820134&device_id=69189073301&ac=wifi&channel=360_new&aid=1128&app_name=aweme&version_code=210&version_name=2.1.0&device_platform=android&ssmix=a&device_type=Redmi+4A&device_brand=Xiaomi&language=zh&os_api=23&os_version=6.0.1&openudid=29f385a1e0b60ece&manifest_version_code=210&resolution=720*1280&dpi=320&update_version_code=2102&_rticket=1565923611254&ts=1565923609&as=a12521d559b1ad39464355&cp=1a17dc5a9562589be1OaWe&mas=01773fb75f7a5086844863aaf3ed01dcd2acaccc2c6c2c9ccc2686
        url = "https://aweme.snssdk.com/aweme/v1/user/follower/list/?user_id="+user_id+"&max_time="+max_time+"&_rticket="+_rticket+"&ts="+str(ts)+"&count=20&retry_type=no_retry&iid=82879820134&device_id=69189073301&ac=wifi&channel=360_new&aid=1128&app_name=aweme&version_code=168&version_name=1.6.8&device_platform=android&ssmix=a&device_type=Redmi+4A&device_brand=Xiaomi&language=zh&os_api=23&os_version=6.0.1&openudid=29f385a1e0b60ece&manifest_version_code=210&resolution=720*1280&dpi=320&update_version_code=2102"
        murl=c.work(url,ts)
        print(c.work(url,ts))
        jsp(murl)

    #"""