websearch.py 文件源码

def _parse_kk(url):
    url = 'https://www.djkakt.us/' + url
    soup = bs4.BeautifulSoup(requests.get(url).text, 'lxml')

    episodes = []
    for epi in soup.find(class_='blog-list')('article'):
        date = epi.find(class_='entry-dateline-link').text
        date = ' '.join(date.split())
        date = arrow.get(date, 'MMMM D, YYYY').format('YYYY-MM-DD')
        title = epi.find(class_='entry-title').text.strip()

        index = _extract_episode_index(title)
        if not index:
            continue

        text = epi.find(class_='sqs-block-content').text
        url = epi.find(class_='entry-title').a['href']
        url = urllib.parse.urljoin('https://www.djkakt.us/', url)

        episodes.append(utils.AttrDict(
            date=date, title=title, index=index, text=text, url=url))

    episodes = list(sorted(episodes, key=lambda x: x.date, reverse=True))
    return episodes