获取法院企业失信信息

#coding:gbk
import sys,re
import urllib.request
#from bs4 import BeautifulSoup
def getId(url,i):
    postdata = urllib.parse.urlencode({‘currentPage‘: i})
    postdata = postdata.encode(‘utf-8‘)
    page = urllib.request.urlopen(url,postdata)
    html =str(page.read(),"utf-8")
    reg=re.compile(r"\[<a .*id=\"(\d+)\">查看.*\]")
    return reg.findall(html)

#===============================================================================
# def getInfo(url):
#     page = urllib.request.urlopen(url)
#     html =str(page.read(),"utf-8")
#     return html
#===============================================================================

fname = "C:/Users/Songxiaodi/Desktop/result.txt"
file = open(fname, ‘w‘)

for i in range(1,3): #页数，根据需要填写，也可以通过正则从网页中分析出来。
    try:
        tt = getId("http://shixin.court.gov.cn/unitMore.do",i)
        print (tt)
        for k in tt: #k 是detail页面的id，每页的id
            html_value="http://shixin.court.gov.cn/detail?id="+k
            html=str(urllib.request.urlopen(html_value).read(),"utf-8")
            html=html.replace("\\n","")
            print(html)
            html=eval(html) #字符串转dict
            file.write(str(html["id"])+";"+html["iname"]+";"+html["caseCode"]+";"+                       html["cardNum"]+";"+html["businessEntity"]+";"+html["courtName"]+";"                       +html["areaName"]+";"+html["partyTypeName"]+";"+html["gistId"]+";"+html["regDate"]+";"                       +html["gistUnit"]+";"+html["duty"]+";"+html["performance"]+";"+html["disruptTypeName"]+";"+html["publishDate"])

            file.write("\n")
    except Exception as err:
        print(err)

file.close()