斗鱼tv爬虫

代码写得很烂，将就着看看吧

import os
import requests
from bs4 import BeautifulSoup

def download(path, url):
    try:
        r = requests.get(url)
        r.raise_for_status
        with open(path, 'wb') as f:
            f.write(r.content)
        return True
    except:
        return False

def get(url):
    try:
        r = requests.get(url)
        r.raise_for_status
        r.encoding = 'utf-8'
    except:
        return False
    soup = BeautifulSoup(r.text, 'html.parser')
    title = soup.find('p', {'class':'listcustomize-topcon-p'})
    floder = title['title']
    print(floder)
    if not os.path.exists(floder):
        os.mkdir(floder)
    os.chdir('./' + floder)
    print("当前工作目录为 : %s" % os.getcwd())
    position = soup.find('div', attrs = {'id':'live-list-content'})
    tags = position.find_all('li')
    infos = []
    errors = []
    for tag in tags:
        info = []
        name = tag.a.find('span', attrs = {'class':'dy-name ellipsis fl'})
        if not name:
            errors.append(tag.a.img['data-original'])
            continue
        info.append(name.string)
        info.append(tag.a['data-rid'])
        info.append(tag.a.img['data-original'])
        path = './' + info[0] + '：' + info[1] + '.' + info[2].split('.')[-1]
        if download(path, info[-1]):
            print(info)
        else:
            errors.append(info[-1])
    return errors


url = 'https://www.douyu.com/directory/game/How'
errors = get(url)
print("error url:", errors)

运行结果：