python爬取豆瓣top250电影

所用python3.7+正则表达式

# encoding: utf-8
import json
import requests
from requests.exceptions import RequestException
import re
import time

def get_one_page(url):
    try:
        headers = {
            'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_13_3) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/65.0.3325.162 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('<em class="">(.*?)</em>.*?<img width="100" alt="(.*?)" src=',re.S)                                   
    items = re.findall(pattern, html)
    for item in items:
        yield {
            'index': item[0],
           
            'title': item[1]
        }

def write_to_file(content):
    with open('doubanTop250.txt', 'a', encoding='utf-8') as f:
        f.write(json.dumps(content, ensure_ascii=False) + '\n')

def main(start):
    url = 'https://movie.douban.com/top250?start='+str(start)+'&filter='
    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(start=i * 25)
        time.sleep(1)