python+fiddler实战——3.爬虫京东网站

import requests
from requests.exceptions import RequestException
import re
import csv
import threadpool#需要先安装：pip install threadpool
#文件保存路径
path=‘E:\data.csv’
#访问网址
baseUrl = ‘https://maoyan.com/board/4?offset=’

def parseOnePage(url):
try:
response = requests.get(url)
except RequestException:
print(url+‘url请求发生异常’)
return None
if response.status_code!=200:
print(‘状态码不为200，’+url+’ 响应异常’)
return None
else:#正常响应
html = response.text
pattern = re.compile(#正则表达式
‘

. ?board-index.?>(\d+). ?class=“name”>?<a. ?>(.?). ?class=“star”>(.?)

. ?“releasetime”>(.?). ?class=“score”.?“integer”>(. ?).?“fraction”>(.