bangumi_bot.py 文件源码

def get_data(self):
        config = {
            'proxy_host': '124.88.67.32',
            'proxy_port': 843
        }
        content = yield httpclient.AsyncHTTPClient().fetch(self.url, **config)
        # content = httpclient.HTTPClient().fetch(self.url)
        if not content.error:
            root = html.fromstring(content.body.decode('utf-8'))
        else:
            # return None
            raise gen.Return(None)

        bangumi_info = []
        # weekday = -1
        for e in root.xpath('//*[@id="scrollContent-day_update"]//*[@class="week-updateList_each"]'):
            weekday = self.WEEKDAY[e.xpath('./div/span')[0].text]
            for record in e.xpath('.//li'):
                url = record.xpath('./a')[0].attrib['href']
                title = record.xpath('./a/div/div[@class="week-cont_title"]')[0].text

                info = {'weekday': weekday,
                        'url': url,
                        'title': title,
                        'update_time': None}

                bangumi_info.append(info)
        raise gen.Return(bangumi_info)