threads.py 文件源码

def scrape(self, pagenum: int) -> None:
        try:
            url = self.source_url.format(pagenum + 1)
            req = requests.get(url, headers={'User-Agent': self.user_agent}, proxies=self.proxy)
            bs = BeautifulSoup(req.text, 'lxml')
            posts = bs('div', class_='post')
            for post in posts:
                dlsize = post.find('h2').get_text().strip()
                table_row = [
                    post.find('div', class_='p-c p-c-time').get_text().strip(),
                    post.find('a', class_='p-title').get('href').strip(),
                    post.find('a', class_='p-title').get_text().strip(),
                    dlsize[dlsize.rfind('(') + 1:len(dlsize) - 1]
                ]
                self.addRow.emit(table_row)
        except HTTPError:
            sys.stderr.write(sys.exc_info()[0])
            QMessageBox.critical(self, 'ERROR NOTIFICATION', sys.exc_info()[0])
            # self.exit()