【python】爬取猫眼电影TOP100代码分享

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


def get_one_page(url):
    #获取每页URL返回的页面数据
    try:
        headers = {
            'User-Agent':'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36',
        }
        response = requests.get(url,headers=headers)
        if response.status_code == 200:
            return response.text
        return None
    except RequestException:
        return None

def parse_one_page(html):
    #通过正则表达式筛选所需内容
    pattern = re.compile(
        '<dd>.*?board-index.*?>(.*?)</i>.*?data-src="(.*?)".*?name.*?a.*?>(.*?)</a>.*?            star.*?>(.*?)</p>.*?releasetime.*?>(.*?)</p>.*?integer.*?>(.*?)</i>.*?fraction.*?>(.*?)</i>.*?</dd>',re.S
    )
    items = re.findall(pattern,html)
    # print(items)
    for item in items:
        yield{
            'index':item[0],
            'image':item[1],
            'title':item[2].strip(),
            'actor':item[3].strip()[3:] if len(item[3]) > 3 else '',
            'time':item[4].strip()[5:] if len(item[4]) > 5 else '',
            'score':item[5].strip()+item[6].strip()
        }

def write_to_file(content):
    #写入本地文件'top100.json'
    with open('TOP100.json','a',encoding='utf-8') as f:
        f.write(json.dumps(content,ensure_ascii=False)+'\n')

def main(offset):
    #访问页面翻页设置
    url = 'http://maoyan.com/board/4?offset='+str(offset)
    html = get_one_page(url)
    items = parse_one_page(html)
    for item in items:
        print(item)
        write_to_file(item)

if __name__ == '__main__':
    #通过time.sleep控制爬取时间间隔
    for i in range(10):
        main(offset=i*10)
        time.sleep(1)

直接送上源码，整体代码框架来自《python3网络爬虫开发实战》一书。