def freeProxyThird(days=1):
"""
ip181 http://www.ip181.com/ 不能用了
:param days:
:return:
"""
url = 'http://www.ip181.com/'
html_tree = getHtmlTree(url)
try:
tr_list = html_tree.xpath('//tr')[1:]
for tr in tr_list:
yield ':'.join(tr.xpath('./td/text()')[0:2])
except Exception as e:
pass
def freeProxySeventh():
"""
快代理 https://www.kuaidaili.com
"""
url_list = [
'https://www.kuaidaili.com/free/inha/{page}/',
'https://www.kuaidaili.com/free/intr/{page}/'
]
for url in url_list:
for page in range(1, 2):
page_url = url.format(page=page)
tree = getHtmlTree(page_url)
proxy_list = tree.xpath('.//table//tr')
for tr in proxy_list[1:]:
yield ':'.join(tr.xpath('./td/text()')[0:2])
def freeProxyTwelve(page_count=2):
"""
guobanjia http://ip.jiangxianli.com/?page=
免费代理库
超多量
:return:
"""
for i in range(1, page_count + 1):
url = 'http://ip.jiangxianli.com/?page={}'.format(i)
html_tree = getHtmlTree(url)
tr_list = html_tree.xpath(
"/html/body/div[1]/div/div[1]/div[2]/table/tbody/tr")
if len(tr_list) == 0:
continue
for tr in tr_list:
yield tr.xpath("./td[2]/text()")[0] + ":" + tr.xpath(
"./td[3]/text()")[0]
def crawl_data5u():
url = 'http://www.data5u.com/'
html_tree = getHtmlTree(url)
print(html_tree)
ul_list = html_tree.xpath('//ul[@class="l2"]')
key = 'ABCDEFGHIZ'
for ul in ul_list:
try:
ip = ul.xpath('./span[1]/li/text()')[0]
classnames = ul.xpath('./span[2]/li/attribute::class')[0]
classname = classnames.split(' ')[1]
port_sum = 0
for c in classname:
port_sum *= 10
port_sum += key.index(c)
port = port_sum >> 3
yield '{}:{}'.format(ip, port)
except Exception as e:
print(e)
def freeProxyFirst(page=10):
"""
无忧代理 http://www.data5u.com/
几乎没有能用的
:param page: 页数
:return:
"""
url_list = [
'http://www.data5u.com/',
'http://www.data5u.com/free/gngn/index.shtml',
'http://www.data5u.com/free/gnpt/index.shtml'
]
for url in url_list:
html_tree = getHtmlTree(url)
ul_list = html_tree.xpath('//ul[@class="l2"]')
for ul in ul_list:
try:
yield ':'.join(ul.xpath('.//li/text()')[0:2])
except Exception as e:
print(e)
def freeProxyFourth(page_count=2):
"""
西刺代理 http://www.xicidaili.com
:return:
"""
url_list = [
'http://www.xicidaili.com/nn/', # 高匿
'http://www.xicidaili.com/nt/', # 透明
]
for each_url in url_list:
for i in range(1, page_count + 1):
page_url = each_url + str(i)
tree = getHtmlTree(page_url)
proxy_list = tree.xpath(
'.//table[@id="ip_list"]//tr[position()>1]')
for proxy in proxy_list:
try:
yield ':'.join(proxy.xpath('./td/text()')[0:2])
except Exception as e:
pass
def freeProxySecond(area=33, page=1):
"""
代理66 http://www.66ip.cn/
:param area: 抓取代理页数，page=1北京代理页，page=2上海代理页......
:param page: 翻页
:return:
"""
area = 33 if area > 33 else area
for area_index in range(1, area + 1):
for i in range(1, page + 1):
url = "http://www.66ip.cn/areaindex_{}/{}.html".format(
area_index, i)
html_tree = getHtmlTree(url)
tr_list = html_tree.xpath(
"//*[@id='footer']/div/table/tr[position()>1]")
if len(tr_list) == 0:
continue
for tr in tr_list:
yield tr.xpath("./td[1]/text()")[0] + ":" + tr.xpath(
"./td[2]/text()")[0]
break
def freeProxyFifth():
"""
guobanjia http://www.goubanjia.com/
:return:
"""
url = "http://www.goubanjia.com/"
tree = getHtmlTree(url)
proxy_list = tree.xpath('//td[@class="ip"]')
# 此网站有隐藏的数字干扰，或抓取到多余的数字或.符号
# 需要过滤掉<p style="display:none;">的内容
xpath_str = """.//*[not(contains(@style, 'display: none'))
and not(contains(@style, 'display:none'))
and not(contains(@class, 'port'))
]/text()
"""
for each_proxy in proxy_list:
try:
# :符号裸放在td下，其他放在div span p中，先分割找出ip，再找port
ip_addr = ''.join(each_proxy.xpath(xpath_str))
port = each_proxy.xpath(
".//span[contains(@class, 'port')]/text()")[0]
yield '{}:{}'.format(ip_addr, port)
except Exception as e:
pass