requests和正则表达式爬取猫眼电影Top100练习

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


# 抓取单页内容
def get_one_page(url):
    headers = {"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) "
                             "Chrome/85.0.4183.121 Safari/537.36"}
    try:
        response = requests.get(url, headers=headers)
        if response.status_code == 200:
            return response.text
        else:
            return None
    except RequestException:
        return None


# 解析单页内容
def parser_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)
    contents = re.findall(pattern, html)
    for content in contents:
        yield {                                   # 生成一个generator，对区域内的内容进行迭代处理
            'index': content[0],
            'image': content[1],
            'name': content[2].strip(),
            'actor': content[3].strip()[3:],
            'time': content[4][5:],
            'score': content[5]+content[6]
        }


# 将单页内容写入文件
def write_to_file(content):
    with open('猫眼电影.txt', 'a', encoding='utf-8') as f:
        f.write(json.dumps(content, ensure_ascii=False) + '\n')
        f.close()


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

if __name__ == "__main__":
    time1 = time.time()
    for i in range(0, 100, 10):
        main(i)
    time2 = time.time()
    pool = Pool()    # 使用多进程提高爬取效率
    pool.map(main, [i*10 for i in range(0, 10)])
    time3 = time.time()
    print(time2-time1)    # for...in花费时间
    print(time3-time2)    # 多线程花费时间

运行时间如下：

 补充对yield用法的理解：

相关博客文章：https://blog.csdn.net/qq_33472765/article/details/80839417