def crawl_xicidaili(self):
"""
获取代理:www.xicidaili.com
方法:正则
"""
for i in range(1, 3):
start_url = 'http://www.xicidaili.com/nn/{}'.format(i)
headers = {
'Accept':
'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8',
'Cookie':
'_free_proxy_session=BAh7B0kiD3Nlc3Npb25faWQGOgZFVEkiJWRjYzc5MmM1MTBiMDMzYTUzNTZjNzA4NjBhNWRjZjliBjsAVEkiEF9jc3JmX3Rva2VuBjsARkkiMUp6S2tXT3g5a0FCT01ndzlmWWZqRVJNek1WanRuUDBCbTJUN21GMTBKd3M9BjsARg%3D%3D--2a69429cb2115c6a0cc9a86e0ebe2800c0d471b3',
'Host': 'www.xicidaili.com',
'Referer': 'http://www.xicidaili.com/nn/3',
'Upgrade-Insecure-Requests': '1',
}
html = get_page(start_url, options=headers)
if html:
find_trs = re.compile('<tr class.*?>(.*?)</tr>', re.S)
trs = find_trs.findall(html)
for tr in trs:
find_ip = re.compile('<td>(\d+\.\d+\.\d+\.\d+)</td>')
re_ip_address = find_ip.findall(tr)
find_port = re.compile('<td>(\d+)</td>')
re_port = find_port.findall(tr)
for address, port in zip(re_ip_address, re_port):
address_port = address + ':' + port
yield address_port.replace(' ', '')
def crawl_89ip(self):
"""
获取代理:www.89ip.cn
方法:正则
"""
start_url = 'http://www.89ip.cn/apijk/?&tqsl=1000&sxa=&sxb=&tta=&ports=&ktip=&cf=1'
html = get_page(start_url)
if html:
find_ips = re.compile('(\d+\.\d+\.\d+\.\d+:\d+)', re.S)
ip_ports = find_ips.findall(html)
for address_port in ip_ports:
yield address_port
def crawl_ip3366(self):
"""
获取代理:www.ip3366.net
方法:正则
"""
for page in range(1, 4):
start_url = 'http://www.ip3366.net/free/?stype=1&page={}'.format(
page)
html = get_page(start_url)
ip_address = re.compile('<tr>\s*<td>(.*?)</td>\s*<td>(.*?)</td>')
re_ip_address = ip_address.findall(html)
for address, port in re_ip_address:
result = address + ':' + port
yield result.replace(' ', '')
def crawl_kxdaili(self):
"""
获取代理:www.kxdaili.com
方法:正则
"""
for i in range(1, 11):
start_url = 'http://www.kxdaili.com/ipList/{}.html#ip'.format(i)
html = get_page(start_url)
ip_address = re.compile(
'<tr.*?>\s*<td>(.*?)</td>\s*<td>(.*?)</td>')
re_ip_address = ip_address.findall(html)
for address, port in re_ip_address:
result = address + ':' + port
yield result.replace(' ', '')
def crawl_premproxy(self):
"""
获取代理:premproxy.com
方法:正则
"""
for i in ['China-01', 'China-02', 'China-03', 'China-04', 'Taiwan-01']:
start_url = 'https://premproxy.com/proxy-by-country/{}.htm'.format(
i)
html = get_page(start_url)
if html:
ip_address = re.compile('<td data-label="IP:port ">(.*?)</td>')
re_ip_address = ip_address.findall(html)
for address_port in re_ip_address:
yield address_port.replace(' ', '')
def crawl_daili66(self, page_count=4):
"""
获取代理:www.66ip.cn
方法:pyquery
"""
start_url = 'http://www.66ip.cn/{}.html'
urls = [start_url.format(page) for page in range(1, page_count + 1)]
for url in urls:
html = get_page(url)
if html:
doc = pq(html)
trs = doc('.containerbox table tr:gt(0)').items()
for tr in trs:
ip = tr.find('td:nth-child(1)').text()
port = tr.find('td:nth-child(2)').text()
yield ':'.join([ip, port])
def crawl_kuaidaili(self):
"""
获取代理:www.kuaidaili
方法:xpath
"""
for i in range(1, 4):
start_url = 'http://www.kuaidaili.com/free/inha/{}/'.format(i)
html = get_page(start_url)
if html:
html = etree.HTML(html,
parser=etree.HTMLParser(encoding='utf-8'))
_ip_xpath = '//*[@id="list"]/table/tbody/tr[{}]/td[1]/text()'
_port_xpath = '//*[@id="list"]/table/tbody/tr[{}]/td[2]/text()'
for i in range(1, 16):
ip_xpath = _ip_xpath.format(i)
port_xpath = _port_xpath.format(i)
ip = html.xpath(ip_xpath)[0]
port = html.xpath(port_xpath)[0]
yield ":".join([ip, port])
def crawl_xroxy(self):
"""
获取代理:www.xroxy.com
方法:正则
"""
for i in ['CN', 'TW']:
start_url = 'http://www.xroxy.com/proxylist.php?country={}'.format(
i)
html = get_page(start_url)
if html:
ip_address1 = re.compile(
"title='View this Proxy details'>\s*(.*).*")
re_ip_address1 = ip_address1.findall(html)
ip_address2 = re.compile(
"title='Select proxies with port number .*'>(.*)</a>")
re_ip_address2 = ip_address2.findall(html)
for address, port in zip(re_ip_address1, re_ip_address2):
address_port = address + ':' + port
yield address_port.replace(' ', '')
def crawl_iphai(self):
"""
获取代理:www.iphai.com
方法:正则
"""
start_url = 'http://www.iphai.com/'
html = get_page(start_url)
if html:
find_tr = re.compile('<tr>(.*?)</tr>', re.S)
trs = find_tr.findall(html)
for s in range(1, len(trs)):
find_ip = re.compile('<td>\s+(\d+\.\d+\.\d+\.\d+)\s+</td>',
re.S)
re_ip_address = find_ip.findall(trs[s])
find_port = re.compile('<td>\s+(\d+)\s+</td>', re.S)
re_port = find_port.findall(trs[s])
for address, port in zip(re_ip_address, re_port):
address_port = address + ':' + port
yield address_port.replace(' ', '')
def crawl_data5u(self):
"""
获取代理:www.data5u.com
方法:正则
"""
start_url = 'http://www.data5u.com/free/gngn/index.shtml'
headers = {
'Accept':
'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8',
'Accept-Encoding':
'gzip, deflate',
'Accept-Language':
'en-US,en;q=0.9,zh-CN;q=0.8,zh;q=0.7',
'Cache-Control':
'max-age=0',
'Connection':
'keep-alive',
'Cookie':
'JSESSIONID=47AA0C887112A2D83EE040405F837A86',
'Host':
'www.data5u.com',
'Referer':
'http://www.data5u.com/free/index.shtml',
'Upgrade-Insecure-Requests':
'1',
'User-Agent':
'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_13_1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.108 Safari/537.36',
}
html = get_page(start_url, options=headers)
if html:
ip_address = re.compile(
'<span><li>(\d+\.\d+\.\d+\.\d+)</li>.*?<li class=\"port.*?>(\d+)</li>',
re.S)
re_ip_address = ip_address.findall(html)
for address, port in re_ip_address:
result = address + ':' + port
yield result.replace(' ', '')