利用Requests + 正则表达式爬取猫眼电影

代码实现

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

def get_one_page(url):
    try:
        response = requests.get(url)
        if response.status_code == 200:
            return response.text
        return None
    except RequestException:
        return None

def parse_one_page(html):
    pattern = re.compile('
.*?board-index.*?>(\d*).*?data-src="(.*?)".*?name">(.*?).*?star">(.*?)
.*?releasetime">(.*?)
'
                          +'.*?integer">(.*?).*?fraction">(.*?).*?
',re.S)
    items = re.findall(pattern, html)

    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('result.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)



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

爬取结果

{"index": "1", "image": "https://p1.meituan.net/movie/20803f59291c47e1e116c11963ce019e68711.jpg@160w_220h_1e_1c", "title": "霸王别姬", "actor": "张国荣,张丰毅,巩俐", "time": "1993-01-01", "score": "9.5"}
{"index": "2", "image": "https://p0.meituan.net/movie/283292171619cdfd5b240c8fd093f1eb255670.jpg@160w_220h_1e_1c", "title": "肖申克的救赎", "actor": "蒂姆·罗宾斯,摩根·弗里曼,鲍勃·冈顿", "time": "1994-10-14(美国)", "score": "9.5"}
{"index": "3", "image": "https://p0.meituan.net/movie/289f98ceaa8a0ae737d3dc01cd05ab052213631.jpg@160w_220h_1e_1c", "title": "罗马假日", "actor": "格利高里·派克,奥黛丽·赫本,埃迪·艾伯特", "time": "1953-09-02(美国)", "score": "9.1"}