Requests+正则表达式爬猫眼电影Top-100

流程框架

• 抓取单页内容：利用requests请求目标站点，得到单个网页HTML代码，返回结果
• 正则表达式分析：根据HTML代码分析得到电影的名称、主演、上映时间、评分、图片链接等信息
• 保存至文件：通过文件的形式将结果保存
• 开启循环及多线程：对多页内容遍历，开启多线程提高抓取速度

实例

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

def get_one_page(url):
    try:
        headers = {
            'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/79.0.3945.130 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)
    #print(items)
    for item in items:
        yield{
            'index':item[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('Maoyan_Top100.txt', 'a', encoding='utf-8') as f:
        f.write(json.dumps(content, ensure_ascii=False)+'\n')
        f.close()

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

# 单进程
if __name__ == '__main__':
    for i in range(10):
        main(i*10)

# 多进程
if __name__ == '__main__':
    pool = Pool()
    pool.map(main, [i*10 for i in range(10)])