def parser(self, html_cont):
'''
:param html_cont: html内容
:return:
'''
if html_cont is None:
return None
soup = BeautifulSoup(html_cont, 'html.parser', from_encoding='utf-8')
subject = soup.find('div', class_="hd").get_text()
links = soup.find_all('a', class_='J-media-item')
html_down = HtmlDownloader()
for link in links:
fileinfo = FileInfo()
# strip() 去除字符串前后空字符
fileinfo.subject = subject.strip()
fileinfo.filename = link.get_text().strip().replace(
':', '_').replace("\r\n", "").replace(u'开始学习',
"").replace(' ', '')
fileinfo.mid = link['href'].split('/')[2]
json = html_down.download(conf.DOWNLOAD_URL.format(
fileinfo.mid)).decode('utf-8').replace('\/', '/')
try:
dic_json = eval(json)
except:
print('error')
fileinfo.url['L'] = dic_json['data']['result']['mpath'][0]
fileinfo.url['M'] = dic_json['data']['result']['mpath'][1]
fileinfo.url['H'] = dic_json['data']['result']['mpath'][2]
# 将
self.res_data.append(fileinfo)
return self.res_data
