self.link.pop()
data_re = '账号 *\d'
pass_re = '\r\n密码.*'
if re.search(data_re, data):
self.data_list.append(data)
if re.search(pass_re, data):
self.pass_list.append(data)
def handle_endtag(self, tag):
if tag == 'a':
self.a_tag = False
if __name__ == '__main__':
html = req.reqs('http://www.aiqiyivip.com/forum-2-1.html', 'gbk')
spider1 = spider()
spider1.feed(html)
for link in spider1.rlink:
vip_page = req.reqs(link, 'gbk')
vip_page.replace('<br>', '')
spider2 = spider()
spider2.feed(vip_page)
re_list = zip(spider2.data_list, spider2.pass_list)
for data in re_list:
for i in data:
print(i.lstrip(), end='')
print()
spider2.close()
print('数据来源：http://www.aiqiyivip.com/')
self.link.pop()
data_re = '账号 *\d'
pass_re = '\r\n密码.*'
if re.search(data_re, data):
self.data_list.append(data)
if re.search(pass_re, data):
self.pass_list.append(data)
def handle_endtag(self, tag):
if tag == 'a':
self.a_tag = False
if __name__ == '__main__':
html = req.reqs('http://www.aiqiyivip.com/forum-2-1.html', 'gbk')
spider1 = spider()
spider1.feed(html)
for link in spider1.rlink:
vip_page = req.reqs(link, 'gbk')
vip_page.replace('<br>', '')
spider2 = spider()
spider2.feed(vip_page)
re_list = zip(spider2.data_list, spider2.pass_list)
for data in re_list:
for i in data:
print(i.lstrip(), end='')
print()
spider2.close()
print('数据来源：http://www.aiqiyivip.com/')
pass
else:
for (name, value) in attrs:
if name == 'title':
if re.search(link_re, value):
title = True
for (name, value) in attrs:
if name == 'href' and title:
self.link.append(value)
def handle_data(self, data):
data_re = '账号\d*'
if re.match(data_re, data):
self.data_list.append(data)
if __name__ == '__main__':
html = req.reqs('http://www.vipfenxiang.com/aiqiyi/')
spider1 = spider()
spider1.feed(html)
result = spider1.link
for link in result:
vip_page = req.reqs(link)
spider2 = spider()
spider2.feed(vip_page)
for data in spider2.data_list:
print(data)
print('数据来源：VIP分享网 http://www.vipfenxiang.com/')
spider1.close()
spider2.close()
else:
for (name, value) in attrs:
if name == 'title':
if re.search(link_re, value):
title = True
for (name, value) in attrs:
if name == 'href' and title:
self.link.append(value)
def handle_data(self, data):
data_re = '账号.*@'
if re.match(data_re, data):
self.data_list.append(data)
if __name__ == '__main__':
html = req.reqs('http://www.vipfenxiang.com/youku/')
spider1 = spider()
spider1.feed(html)
result = spider1.link
print('账号无法使用说明：如果输入密码错误5次就会导致账号被锁，使用人数超过3人看电影就会异常。')
for link in result:
vip_page = req.reqs(link)
spider2 = spider()
spider2.feed(vip_page)
for data in spider2.data_list:
print(data)
print('数据来源：VIP分享网 http://www.vipfenxiang.com/')
spider1.close()
spider2.close()
def handle_starttag(self, tag, attrs):
if tag == 'span':
if len(attrs):
for (name, value) in attrs:
if value == 'articleSection':
self.user = True
if value == 'articleBody':
self.password = True
else:
pass
def handle_data(self, data):
if self.user:
self.user_list.append(data)
self.user = False
if self.password:
self.pass_list.append(data)
self.password = False
if __name__ == '__main__':
html = req.reqs('http://www.9sep.org/free-xunlei-vip')
spiders = spider()
spiders.feed(html)
result = zip(spiders.user_list, spiders.pass_list)
for (username, password) in result:
print('账号{0};密码{1}'.format(username, password))
spiders.close()
print('数据来源：VIP分享吧 http://www.vipfx8.com')
