Python爬虫实现全国失信被执行人名单查询功能示例

版本1代码示例

# -*- coding:utf-8*-
import sys
reload(sys)
sys.setdefaultencoding('utf-8')
import time
import requests
time1=time.time()
import pandas as pd
import json
iname=[]
icard=[]
def person_executed(name):
  for i in range(0,30):
    try:
      url="https://sp0.baidu.com/8aQDcjqpAAV3otqbppnN2DJv/api.php?resource_id=6899" \
      "&query=%E5%A4%B1%E4%BF%A1%E8%A2%AB%E6%89%A7%E8%A1%8C%E4%BA%BA%E5%90%8D%E5%8D%95" \
      "&cardNum=&" \
      "iname="+str(name)+ \
      "&areaName=" \
      "&pn="+str(i*10)+ \
      "&rn=10" \
      "&ie=utf-8&oe=utf-8&format=json"
      html=requests.get(url).content
      html_json=json.loads(html)
      html_data=html_json['data']
      for each in html_data:
        k=each['result']
        for each in k:
          print each['iname'],each['cardNum']
          iname.append(each['iname'])
          icard.append(each['cardNum'])
    except:
      pass
if __name__ == '__main__':
  name="郭**"
  person_executed(name)
  print len(iname)
  #####################将数据组织成数据框###########################
  data=pd.DataFrame({"name":iname,"IDCard":icard})
  #################数据框去重####################################
  data1=data.drop_duplicates()
  print data1
  print len(data1)
  #########################写出数据到excel#########################################
  pd.DataFrame.to_excel(data1,"F:\\iname_icard_query.xlsx",header=True,encoding='gbk',index=False)
  time2=time.time()
  print u'ok,爬虫结束!'
  print u'总共耗时：'+str(time2-time1)+'s'

# -*- coding:utf-8*-
import sys
reload(sys)
sys.setdefaultencoding('utf-8')
import time
import requests
time1=time.time()
import pandas as pd
import json
iname=[]
icard=[]
courtName=[]
areaName=[]
caseCode=[]
duty=[]
performance=[]
disruptTypeName=[]
publishDate=[]
def person_executed(name):
  for i in range(0,30):
    try:
      url="https://sp0.baidu.com/8aQDcjqpAAV3otqbppnN2DJv/api.php?resource_id=6899" \
      "&query=%E5%A4%B1%E4%BF%A1%E8%A2%AB%E6%89%A7%E8%A1%8C%E4%BA%BA%E5%90%8D%E5%8D%95" \
      "&cardNum=&" \
      "iname="+str(name)+ \
      "&areaName=" \
      "&pn="+str(i*10)+ \
      "&rn=10" \
      "&ie=utf-8&oe=utf-8&format=json"
      html=requests.get(url).content
      html_json=json.loads(html)
      html_data=html_json['data']
      for each in html_data:
        k=each['result']
        for each in k:
          print each['iname'],each['cardNum'],each['courtName'],each['areaName'],each['caseCode'],each['duty'],each['performance'],each['disruptTypeName'],each['publishDate']
          iname.append(each['iname'])
          icard.append(each['cardNum'])
          courtName.append(each['courtName'])
          areaName.append(each['areaName'])
          caseCode.append(each['caseCode'])
          duty.append(each['duty'])
          performance.append(each['performance'])
          disruptTypeName.append(each['disruptTypeName'])
          publishDate.append(each['publishDate'])
    except:
      pass
if __name__ == '__main__':
  name="郭**"
  person_executed(name)
  print len(iname)
  #####################将数据组织成数据框###########################
  # data=pd.DataFrame({"name":iname,"IDCard":icard})
  detail_data=pd.DataFrame({"name":iname,"IDCard":icard,"courtName":courtName,"areaName":areaName,"caseCode":caseCode,"duty":duty,"performance":performance,\
               "disruptTypeName":disruptTypeName,"publishDate":publishDate})
  #################数据框去重####################################
  # data1=data.drop_duplicates()
  # print data1
  # print len(data1)
  detail_data1=detail_data.drop_duplicates()
  # print detail_data1
  # print len(detail_data1)
  #########################写出数据到excel#########################################
  pd.DataFrame.to_excel(detail_data1,"F:\\iname_icard_query.xlsx",header=True,encoding='gbk',index=False)
  time2=time.time()
  print u'ok,爬虫结束!'
  print u'总共耗时：'+str(time2-time1)+'s'