def run(self):
print self.url
#先提取单个页面具体链接
pattern = re.compile('<h3><a href="(.*?)html" target="_blank" id="">')
page_url_href = self.get_content(self.url,pattern)
#再去获取具体的页面
page_url_prefix = 'http://t66y.com/'
for item in page_url_href:
page_url = page_url_prefix + item +'html'
#print page_url
try:
download_pattern = re.compile('<a target="_blank" .*?rmdown.*?>(.*?)</a>')
download_content = self.get_src_content(page_url)
download_url = download_pattern.findall(download_content)
if download_url != []:
#获取下载链接
download_url_link = download_url[0]
print download_url_link
#获取标题内容
title_pattern = re.compile('<title>(.*?)</title>')
title_content = title_pattern.findall(download_content)[0]
title_content = title_content.decode('gbk').encode('utf-8')
print title_content
if download_url_link != '':
url_link = Url_Link(title_content,download_url_link)
url_link.save()
time.sleep(1)
except Exception as e:
print 'Run Error '+str(e)+'!'
def delete():
Url_Link.objects(name="delete").delete()
def update():
Url_Link.objects(name="hello").update(link="http://www.163.com")
def save_url():
url = Url_Link(name="hello", link="http://www.baidu.com")
url.save()