Python网络爬虫爬取猫眼电影排行榜

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

def get_one_page(url):
    try:
        headers = {
        'User-Agent':'Mozilla / 5.0(Macintosh;Intel Mac OS X 10_13_3) AppleWebKit / 537.36(KHTML, like Gecko) Chrome / 65.0.3325.162 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):
    pattern = re.compile('<dd>.*?board-index.*?>(\d+)</i>.*?data-src="(.*?)".*?name"><a'
                         + '.*?>(.*?)</a>.*?star">(.*?)</p>.*?releasetime">(.*?)</p>'
                         + '.*?integer">(.*?)</i>.*?fraction">(.*?)</i>.*?</dd>', re.S)
    items = re.findall(pattern,html)
    for item in items:
        yield{
            'index':items[0],
            'image':item[1],
            'title':item[2],
            'actor':item[3].strip()[3:] ,
            'time':item[4].strip()[5:] ,
            'score':item[5] + item[6]
        }

def write_to_file(content):
    with open('result.txt','a',encoding='utf-8') as f:
        f.write(json.dumps(content,ensure_ascii=False)+'\n')

def main(offset):
    url = 'http://maoyan.com/board/4=' + str(offset)
    html = get_one_page(url)
    for item in parse_one_page(html):
        print(item)
        write_to_file(item)

if __name__=='__main__':
    for i in range(10):
        main(offset = i * 10)
        time.sleep(1)



         学习资料：崔庆才网络爬虫

来源：CSDN

作者：六级不过不改名！

链接：https://blog.csdn.net/qq_44789425/article/details/104711152