使用request与正则表达式爬取bangumi动画排行榜

Posted 2021-01-16 wdl1078390625

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.content.decode(‘utf-8‘)
        return None
    except RequestException:
        return None


def parse_one_page(html):
    pattern = re.compile(
        ‘<h3>.*?class="l">(.*?)</a>.*?<small>Rank.*?</small>(d+)</span>‘, re.S)
    items = re.findall(pattern, html)
    print(items)

def main(offset):
    url = ‘http://bangumi.tv/anime/browser?sort=rank&page=‘ + str(offset)
    html = get_one_page(url)
    parse_one_page(html)
    


if __name__ == ‘__main__‘:
    for i in range(1,20):
        main(offset=i)
        time.sleep(1)