程序 request_xkz

# -*- coding: utf-8 -*-
"""
Created on Mon Sep  9 10:07:50 2019

@author: Administrator
"""


import os
import re
import traceback
import requests
import openpyxl
from bs4 import BeautifulSoup
#from write_excel import OpenpyxlExcel
from write_excel import OprationExcel



url = "http://xkz.cbirc.gov.cn/ilicence/showLicenceInfo.do?state=3&id=00000001"
root = "d:/pictures//"
path = root + "xkz.html"
r = requests.get(url)
#r.coding = "utf-8"
html = r.text
soup = BeautifulSoup(html, "html.parser")


# 每条信息的key
info_key_list = []

# 每个key的value
info_value_list = []

# 将每行信息以字典形式存储的列表 json格式
info_list = []

lsh_values_list = []
jgname_values_list = []
jgcode_values_list = []

# 查找的标签中，筛选多条属性时，可用如下方法
# for i in soup.find_all("td", attrs={"align":"right", "height": "25"}):
#print(soup.find("title").string)
try:
    if not soup.find("title").string == "出错啦！":
        for tr in soup.find_all("tr", "a0"):
            if tr.find("td", {"align": "right"}):
                for td in tr.find("td", {"align": "right"}):
                    info_key = td.string.split()[0].split("：")[0]
                    info_key_list.append(info_key)
                    
                # 由于html中有空格、换行等空字符，这里要用next_siblings平行迭代并判断出非空，再输出
                # 但是注意，有些信息的value可能是空的，这里要判断出value为空的key，并把value改为“--”
                for td in tr.find("td", {"align": "right"}).next_siblings:
                    
                    # 判断出bs4中的tag类型，并判断出tag内string为空的内容
                    if type(td).__name__ == ‘Tag‘ and len(td.string.split()) == 0:
                        info_value = "--"
                        info_value_list.append(info_value)
                        
        #            elif not (td.string is None) and (len(td.string.split()) > 0):
                    elif td.string and (len(td.string.split()) > 0):
                        info_value = (td.string.split()[0])
                        info_value_list.append(info_value)
                    else:
                        continue
        
        
    #    print(len(info_key_list))
    #    print((info_value_list))
        for i in range(len(info_key_list)):
            info_list.append({info_key_list[i]: info_value_list[i]})
    #    print(info_list)
#        for num in range(len(info_list)):
#            print(num, info_list[num])
        
    #    excel_1 = OpenpyxlExcel("test.xlsx")
    #    excel_1.openpyxl_write(info_list)
        excel1 = OprationExcel("xkz1.xls")
        excel1.excel_write()
        excel1.excel_append(lsh_values_list, 1)
        excel1.excel_append(jgname_values_list, 2)
        excel1.excel_append(jgcode_values_list, 3)
        excel1.excel_read(1)
        excel1.excel_read(2)
        excel1.excel_read(3)
    #    excel1.excel_append(info_list[1]["机构名称"])
    #    excel1.excel_append(info_list[0]["机构编码"])
    else:
        print("查无结果")
except:
    traceback.print_exc()