猫眼电影top100票房爬虫 Request + 正则

import json
import re
from multiprocessing.pool import Pool

import requests
from requests import RequestException


def get_one_page(url):
    try:
        response =requests.get(url)
        if response.status_code==200:
            return response.text
    except RequestException:
        return None
def parse_one_page(html):
    '''
    对界面进行解析
    :param html:
    :return:
    '''
    pattern=re.compile('<dd>.*?board-index.*?>(\d+)</i>.*?data-src="(.*?)".*?name"><a .*?>(.*?)</a>.*?star">(.*?)</p>.*?releasetime">(.*?)</p>.*?integer">(.*?)</i>.*?fraction">(\d+)</i>',re.S)#正则表达式
    items=re.findall(pattern,html)

    for item in items:
        yield {
            '序号':item[0],
            '图片':item[1],
            '电影名': item[2],
            '主演': item[3].strip()[3:],
            '上映时间': item[4].strip()[5:],
            '评分': item[5]+item[6],
        }

def write_to_file(content):
    '''
    写入文本
    :param content:
    :return:
    '''
    with open('猫眼top100.txt', 'a',encoding='utf-8')as f:#打开文件，如果没有就创建，encoding 指定编码方式
        f.write(json.dumps(content,ensure_ascii=False)+'\n')#ensure_ascii=False以指定的方式编码
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)

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

 

来源：oschina

链接：https://my.oschina.net/u/4267631/blog/3681159