Requests+正则表达式爬取猫眼TOP100电影

Posted 2021-01-30 sanduzxcvbnm

需要着重学习的地方:
(1)爬取分页数据时,url链接的构建
(2)保存json格式数据到文件,中文显示问题
(3)线程池的使用
(4)正则表达式的写法

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

# 抓取单页内容
def get_one_page(url):
    try:
        response = requests.get(url)
        if response.status_code == 200:
            return response.text
        return None
    except RequestException:
        return  None

# 正则表达式分析
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]
        }

#  保存至文件
def write_to_file(content):
    # 注意:把json数据保存到文件中显示出中文
    with open(‘result.txt‘,‘a‘,encoding=‘utf-8‘) as f:
        f.write(json.dumps(content,ensure_ascii=False) + ‘
‘)
        f.close()

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


if __name__ == ‘__main__‘:
    # 开启循环,抓取多页数据
    # for i in range(10):
    #     main(i*10)
    # 使用线程池
    pool = Pool()
    pool.map(main,[i*10 for i in range(10)])