利用requests和正则表达式爬取猫眼电影最受期待排行

最新推荐文章于 2023-01-13 15:58:42 发布

zcharlotteyq

最新推荐文章于 2023-01-13 15:58:42 发布

阅读量146

点赞数

分类专栏：网络爬虫文章标签：正则表达式爬虫

本文链接：https://blog.csdn.net/m0_49119161/article/details/108409748

版权

网络爬虫专栏收录该内容

8 篇文章 1 订阅

订阅专栏

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

def getOnePage(url):
    try:
        headers = {
            'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/78.0.3904.116 Safari/537.36'
        }
        response = requests.get(url, headers=headers)
        if response.status_code==200:
            return response.text
        else:
            return None
    except RequestException:
        return None

def parseOnePage(html):
    pattern = re.compile(
        '<dd>.*?board-index.*?>(\d+)</i>.*?data-src="(.*?)".*?data-val=.*?">(.*?)</a>.*?star">(.*?)</p>.*?releasetime">(.*?)</p>.*?</dd>',re.S
    )
    items = re.findall(pattern, html)
    for item in items:
        yield {
            'index': item[0],
            'pic': item[1],
            'title': item[2],
            'star': item[3],
            'time': item[4]
        }

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

def main(offset):
    url = 'https://maoyan.com/board/6?offset=' + str(offset)
    html = getOnePage(url)
    for item in parseOnePage(html):
        print(item)
        writeToFile(item)

if __name__=='__main__':
    for i in range(5):
        main(offset=i * 10)
        time.sleep(1)