利用正则爬取猫眼电影

爬取猫眼电影

import json
import requests
from requests.exceptions import RequestException
import re

def get_one_page(url):#获取一个页面的信息
    try:
        kv = {"user-agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/76.0.3809.100 Safari/537.36"}
        # proxies=get_random_ip(proxies)
        response=requests.get(url,headers=kv)
        response.encoding='utf-8'
        if response.status_code==200:
            return response.text
        return None
    except RequestException:
        return None

def parse_one_page(html):#解析页面信息,每个匹配元素后面必须要加结束符号

 pattern=re.compile('<dd>.*?board-index.*?>(\d+)</i>.*?data-src="(.*?)".*?name"><a'
                       +'.*?>(.*?)</a>.*?star">(.*?)</p>.*?releasetime">(.*?)</p>&