爬取排污许可证所有详细信息2020.5.28

from tkinter import *  # 导入窗口控件
import requests
from lxml import etree
from tkinter import ttk
from bs4 import BeautifulSoup
import webbrowser  # 调用浏览器打开网页
from tkinter import messagebox  # 弹出提示框
from openpyxl import Workbook
import time  #延时

treedata1=[]   #全局变量用于存储查询到企业详细信息数据
def download_song():
    # 打开查询页面，得到页面总数....................................................
    datas = {
   "page.pageNo": "1",
             "page.orderBy": "",
             "page.order": "",
             "province": "210000000000",
             "city": "211300000000",
             "registerentername": "",
             "xkznum": "",
             "treadname": "",
             "treadcode": "",
             "publishtime": ""}
    url = "http://permit.mee.gov.cn/permitExt/syssb/xkgg/xkgg!licenseInformation.action"
    r = requests.post("http://permit.mee.gov.cn/permitExt/syssb/xkgg/xkgg!licenseInformation.action", data=datas)
    r = requests.post(url, data=datas)
    html = etree.HTML(r.text)
    urlpage = html.xpath('//div[@class="fr margin-t-33 margin-b-20"]/a/@onclick')[5]  # 找到HTML中总页数
    urlpageidstr = urlpage[21:23]  # 截取字符串，得到总页数
    # 开始爬取所有页面数据
    start_page = 1
    #urlpageidstr=(int(urlpageidstr))
    urlpageidstr = 2  # 调试数据暂定为2页，提高效率
    messagebox.showinfo("提示", "数据正在读取请稍候。。。。")
    for page in range(start_page, urlpageidstr):
        content = page
    # 打开查询页面，得到每个具体企业信息的链接....................................................
        urlpage = content
        datas = {
   "page.pageNo": urlpage,
             "page.orderBy": "",
             "page.order": "",
             "province": "210000000000",
             "city": "211300000000",
             "registerentername": "",
             "xkznum": "",
             "treadname": "",
             "treadcode": "",
             "publishtime": ""}
        url = "http://permit.mee.gov.cn/permitExt/syssb/xkgg/xkgg!licenseInformation.action"
        r = requests.post("http://permit.mee.gov.cn/permitExt/syssb/xkgg/xkgg!licenseInformation.action", data=datas)
        r = requests.post(url, data=datas)
        html = etree.HTML(r.text)
        href_url = html.xpath('//table[@class="tabtd"]/tr/td/a/@href')
        href_name = html.xpath('//table[@class="tabtd"]/tr')[1:]
        urlpage = html.xpath('//div[@class="fr margin-t-33 margin-b-20"]/a/@onclick')[5]  # 找到HTML中总页数
        #urlpageidstr = urlpage[21:23]  # 截取字符串，得到总页数
        #print(urlpageidstr)
        i = 0
        datasum=0 #记录爬取数据个数
        # 打开查询页面，得到第N个企业的详细 信息....................................................
        for href_url, roos in zip(href_url, href_name):
            addurl = href_url
            name = roos.xpath('./td[4]/text()')[0]
            i = i + 1
            addurl = addurl[39:93]
            datas = {
   "xkgk": "getxxgkContent",
                 "dataid": addurl}
            url = "http://permit.mee.gov.cn/permitExt/xkgkAction!xkgk.action?xkgk=" + addurl
            html = requests.get(url, headers=datas)
            soup = BeautifulSoup(html.text, 'lxml')
            name_id = soup.find_all('p', style="font-size:36px;")[0].text  # 得到企业名称
            name_add = soup.find_all('p', style="font-weight: bold;color: green;font-size: 14px;")[0].text  # 得到企业地址等信息 ..strip() 属性删除空格
            content = name_add
            content = content.strip()  # 删除字符串左边空格
            content = content.split()  # 拆分字符串，通过指定分隔符对字符串进行分割，默认是空格。rstrip("\xa0\xa0\xa0\xa0\r\n\t\t\t")
            # content=content.partition(":")
            str2 = ''.join(content)
            u1, u2, u3, u4, u5 = str2.split('：', 4)
            f1 = u2.find('行业类别')
            f2 = u2[0:f1]
            g1 = u3.find('所在地区')
            g2 = u3[0:g1]
            h1 = u4.find('发证机关')
            h2 = u4[0:h1]
            #ii = str(i)
            paiwuxukebianhao=soup.find_all('table', class_="tab0")[0].text.strip