[置顶] 【python爬虫】网贷天眼平台表格数据抓取

# -*- coding:utf-8*-
import sys
reload(sys)
sys.setdefaultencoding('utf-8')
import time
time1=time.time()
import requests
from lxml import etree
import re
import pandas as pd

url="http://www.p2peye.com/shuju/ptsj/"
head={
"Host": "www.p2peye.com",
"Connection": "keep-alive",
"Cache-Control": "max-age=0",
"Upgrade-Insecure-Requests": "1",
"User-Agent": "Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.36",
"Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8",
"Accept-Encoding": "gzip, deflate, sdch",
"Accept-Language": "zh-CN,zh;q=0.8"
}

html=requests.get(url,headers=head).content
selector=etree.HTML(html)

num1=[]
name1=[]
total1=[]
rate1=[]
pnum1=[]
cycle1=[]
p1num1=[]
fuload1=[]
alltotal1=[]
capital1=[]

#############用正则表达式匹配
num=re.findall('<td class="num">(.*?)</td>',html,re.S)
for each in num:
print each
num1.append(each)

##############用xpath解析平台名称
name=selector.xpath('//td[@class="name"]//a/text()')
for each in name:
print each
name1.append(each)

#############用xpath解析成交额
total=selector.xpath('//td[@class="total"]/text()')
for each in total:
print each
total1.append(each)

#############用xpath解析综合利率
rate=selector.xpath('//td[@class="rate"]/text()')
for each in rate:
print each
rate1.append(each)

#############用xpath解析投资人
pnum=selector.xpath('//td[@class="pnum"]/text()')
for each in pnum:
print each
pnum1.append(each)

#############用xpath解析借款周期
cycle=selector.xpath('//td[@class="cycle"]/text()')
for each in cycle:
print each
cycle1.append(each)

#############用xpath解析借款人
p1num=selector.xpath('//td[@class="p1num"]/text()')
for each in p1num:
print each
p1num1.append(each)

#############用xpath解析满标速度
fuload=selector.xpath('//td[@class="fuload"]/text()')
for each in fuload:
print each
fuload1.append(each)

#############用xpath解析累计贷款余额
alltotal=selector.xpath('//td[@class="alltotal"]/text()')
for each in alltotal:
print each
alltotal1.append(each)

##############用xpath解析资金净流入
capital=selector.xpath('//td[@class="capital"]/text()')
for each in capital:
print each
capital1.append(each)

data=pd.DataFrame({"排序":num1,"平台名称":name1,"成交额":total1,"综合利率":rate1,"投资人":pnum1,"借款周期":cycle1,"借款人":pnum1,"满标速度":fuload1,\
"累计贷款余额":alltotal1,"资金净流入":capital})

print data

####################写入excel
pd.DataFrame.to_excel(data, "C:\\wang_data.xlsx", header=True, encoding='gbk', index=False)
################计算当前时间
time2 = time.time()
print u'ok,爬虫结束!'
print u'总共耗时：' + str(time2 - time1) + 's'