def get_66ip_proxies(num=50):
url = "http://m.66ip.cn/mo.php?sxb=&tqsl={}&port=&export=&ktip=&sxa=&submit=%CC%E1++%C8%A1&textarea=".format(
num)
html = getHTMLText(url, headers = HEADERS)
pattern = re.compile("\d+\.\d+\.\d+\.\d+\:\d+")
proxies = pattern.findall(html)
for proxy in proxies:
yield proxy
def freeProxyFirst():
"""
抓取米扑代理 http://proxy.mimvp.com/api/fetch.php?orderid=860170713165250819
：return:
"""
url = 'http://proxy.mimvp.com/api/fetch.php?orderid=860170713165250819'
html = getHTMLText(url, headers=HEADER())
proxy_list = html.split('\r\n')
for proxy in proxy_list:
yield proxy
def freeProxySecond(proxy_number=100):
"""
抓取代理66 http://www.66ip.cn/
:param proxy_number: 代理数量
:return:
"""
url = "http://m.66ip.cn/mo.php?sxb=&tqsl={}&port=&export=&ktip=&sxa=&submit=%CC%E1++%C8%A1&textarea=".format(
proxy_number)
html = getHTMLText(url, headers=HEADER())
for proxy in re.findall(r'\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3}:\d{1,5}',
html):
yield proxy