1. # -*- coding = ut-8 -*-
    2. # @Time : 2021/6/2 9:23
    3. # @Author : PHC
    4. # @File cjcyw_goods.py
    5. # @Software : PyCharm
    7. import json
    8. import requests
    9. import urllib
    10. import xlwt
    11. import  time
    12. import os
    13. import shutil
    15. #每访问的地址都不一样，将地址传参的形式代入
    16. def messageAll(url):
    17.     head={
    18.         "Cookie":"cjcy_session_id=a7ff8f24-fcb2-43d3-80e4-53a7d466cea9",
    19.         "User-Agent":"cicy/5.5 (iPhone; iOS 12.0; Scale/3.00)",
    20.         "Content-Type": "application/x-www-form-urlencoded",
    21.         "Host": "t.cjcyw.com"
    22.     }
    23.     request=urllib.request.Request(url,headers=head)
    24.     response=urllib.request.urlopen(request)
    25.     pages=response.read().decode("utf-8")
    26.     contents=json.loads(pages)
    27.     return  contents
    29. def main():
    30.     datalist = []
    31.     pageNum=2                   #查找的页数
    32.     for num in range(1,pageNum+1):      #左闭右开，打印1 ，2 ，3
    33.         urlOne="https://t.cjcyw.com/cjcy/goods/list?_index={}".format(num)            #所需要查找的页数,循环
    35.         contents=messageAll(urlOne)
    36.         content=contents['data']['records']
    38.         for i in content:
    39.             data=[]
    40.             starDate = i['time1']
    41.             loadTime = time.strftime("%Y-%m-%d", time.localtime(starDate))
    42.             data.append(loadTime)  # 装货日期
    44.             starLoacation=i['dangqian']
    45.             data.append(starLoacation)      #始发港
    47.             endLocation=i['mudidi']
    48.             data.append(endLocation)            #目的港
    50.             cargo = i['title']
    51.             data.append(cargo)               # 货物
    52.             aid=i['aid']
    53.             dunwei=i['dunwei']
    54.             data.append(dunwei)                        #货物重量
    56.             #查看每条船的详情信息
    57.             urlEnd="https://t.cjcyw.com/cjcy/goods/detail?aid={}".format(aid)
    58.             contentEnd=messageAll(urlEnd)
    59.             contentLast=contentEnd['data']
    61.             name=contentLast['publishLinkMan']
    62.             data.append(name)                         #名字
    63.             phone=contentLast['publishTel']
    64.             data.append(phone)                   #联系电话
    65.             beizhu = contentLast['beizhu11']
    66.             data.append(beizhu)                      #备注
    67.             data.append("长江船运网-货源")            #来源，加到最后
    68.             datalist.append(data)
    69.             print("第", num, "页，第", len(datalist), "条", data)
    71.     timePass = time.localtime()          # 输出系统的当前时间，当前时间为格林尼治时间？ 秒数，
    72.     timeNow = time.strftime("%Y-%m-%d", timePass)        # 将系统的当前时间格式化输出，一天打印一次，若重复打印，最好将已输出的文件名字更改一下，避免数据丢失，重名会覆盖。
    73.     savePath = "%s长江船运网-----货源.xls" % (timeNow)  # 保存的文件命名格式：当前时间（年-月-日）+文件名
    74.     table = xlwt.Workbook(encoding="utf-8", style_compression=0)
    75.     sheet = table.add_sheet("货源信息-长江船运网", cell_overwrite_ok=True)
    76.     col = ("装货日期", "起始地", "到达地", "货物类型", "货物重量", "名字", "联系电话", "备注","来源")
    77.     for i in range(0, len(col)):
    78.         sheet.write(0, i, col[i])
    80.     for i in range(len(datalist)):
    81.         oneShip=datalist[i]
    82.         for j in range(0,len(col)):
    83.             a=oneShip[j]
    84.             sheet.write(i+1,j,a)
    85.     table.save(savePath)                    #文件保存到当前目录
    87.     nowDirectory=os.getcwd()         #返回当前工作的目录
    88.     file_path=os.path.join(nowDirectory,savePath)           #返回当前目录中指定的文件。
    89.     new_path=r'D:\长江船运网爬取文档\货源'                 #将文件保存到指定目录
    90.     shutil.move(file_path,new_path)
    93. if  __name__=='__main__':
    94.     main()
    95.     print("打印完毕")