def get_proxies(self):
get_log_config()
proxy_model_list = []
print('正在爬取快代理......')
response = super(KuaidailiSpider, self).get_proxies()
pattern = re.compile(
'<tr>\s.*?<td.*?>(.*?)</td>\s.*?<td.*?>(.*?)</td>\s.*?<td.*?>(.*?)</td>\s.*?<td.*?>('
'.*?)</td>\s.*?<td.*?>(.*?)</td>\s.*?<td.*?>(.*?)</td>\s.*?<td.*?>(.*?)</td>\s.*?</tr>',
re.S
)
infos = re.findall(pattern, response.text)
for item in infos:
try:
ip = item[0]
port = item[1]
anonymity = item[2]
http_type = item[3]
area = item[4]
speed = item[5]
print(ip + " | " + port + " | " + anonymity + " | " + http_type + " | " + area + " | " + speed)
if http_type == 'HTTP' or http_type == 'HTTPS':
proxy = Proxy()
proxy.set_ip(ip)
proxy.set_port(port)
proxy.set_http_type(http_type.lower())
proxy.set_anonymity(anonymity)
proxy.set_area(area)
proxy.set_speed(speed)
proxy.set_agent(self.agent)
proxy.set_survival_time("")
proxy_model_list.append(proxy)
except Exception as e:
logging.debug(e)
logging.debug(f"抓取 {self.agent} 网站共计 {len(proxy_model_list)} 个代理")
return proxy_model_list
def get_proxies(self):
# 加载 Log 配置
get_log_config()
proxy_model_list = []
print('正在爬取无忧代理……')
response = super(Data5uSpider, self).get_proxies()
selector = etree.HTML(response.text)
infos = selector.xpath('//ul[@class="l2"]')
for i, info in enumerate(infos):
try:
ip = info.xpath('//ul[@class="l2"]/span[1]/li/text()')[i] # ip
port = info.xpath('//ul[@class="l2"]/span[2]/li/text()')[
i] # 端口
anonymity = info.xpath(
'//ul[@class="l2"]/span[3]/li/a/text()')[i] # 匿名度
http_type = info.xpath(
'//ul[@class="l2"]/span[4]/li/a/text()')[i] # 类型
area = info.xpath('//ul[@class="l2"]/span[6]/li/a[1]/text()')[
i] # 地区, 省
area = area + info.xpath(
'//ul[@class="l2"]/span[6]/li/a[2]/text()')[i] # 地区, 市
speed = info.xpath('//ul[@class="l2"]/span[8]/li/text()')[
i] # 速度
print(ip + " | " + port + " | " + anonymity + " | " +
http_type + " | " + area + " | " + speed + " | ")
if http_type == 'http' or http_type == 'https':
# print(http_type + "://" + ip + ":" + port)
proxy = Proxy()
proxy.set_ip(ip)
proxy.set_port(port)
proxy.set_http_type(http_type)
proxy.set_anonymity(anonymity)
proxy.set_area(area)
proxy.set_speed(speed)
proxy.set_agent(self.agent)
proxy.set_survival_time("")
proxy_model_list.append(proxy)
else:
pass
except Exception as e:
logging.debug(e)
logging.debug("抓取 " + self.agent + " 网站共计 " +
str(len(proxy_model_list)) + " 个代理")
return proxy_model_list
def get_proxies(self):
# 加载 Log 配置
get_log_config()
proxy_model_list = []
print('正在爬取快代理……')
response = super(KuaidailiSpider, self).get_proxies()
pattern = re.compile(
'<tr>\s.*?<td.*?>(.*?)</td>\s.*?<td.*?>(.*?)</td>\s.*?<td.*?>(.*?)</td>\s.*?<td.*?>('
'.*?)</td>\s.*?<td.*?>(.*?)</td>\s.*?<td.*?>(.*?)</td>\s.*?<td.*?>(.*?)</td>\s.*?</tr>',
re.S)
infos = re.findall(pattern, response.text)
for item in infos:
try:
ip = item[0] # ip
port = item[1] # 端口
anonymity = item[2] # 匿名度
http_type = item[3] # 类型
area = item[4] # 地区
speed = item[5] # 速度
print(ip + " | " + port + " | " + anonymity + " | " +
http_type + " | " + area + " | " + speed)
if http_type == 'HTTP' or http_type == 'HTTPS':
# print(type.lower() + "://" + ip + ":" + port)
proxy = Proxy()
proxy.set_ip(ip)
proxy.set_port(port)
proxy.set_http_type(http_type.lower())
proxy.set_anonymity(anonymity)
proxy.set_area(area)
proxy.set_speed(speed)
proxy.set_agent(self.agent)
proxy.set_survival_time("")
proxy_model_list.append(proxy)
except Exception as e:
logging.debug(e)
logging.debug("抓取 " + self.agent + " 网站共计 " +
str(len(proxy_model_list)) + " 个代理")
return proxy_model_list
def case_10():
dao = ProxyDBManager()
dao.create_proxy_table()
proxy = Proxy()
ip = '125.115.141.6'
port = 8118
http_type = 'HTTPS'
anonymity = '高匿'
area = '浙江宁波'
speed = '0.148秒'
agent = 'agent'
survival_time = '4小时'
proxy.set_ip(ip)
proxy.set_port(port)
proxy.set_type(http_type)
proxy.set_anonymity(anonymity)
# 处理空地区
if area is None:
proxy.set_area('')
else:
proxy.set_area(area)
proxy.set_speed(speed)
proxy.set_agent(agent)
proxy.set_survival_time(survival_time)
dao.insert_proxy_table(proxy)
proxy_address = dao.select_random_proxy()
print(proxy_address)
if 'http://' in proxy_address:
proxy_address = proxy_address.replace('http://', '')
else:
proxy_address = proxy_address.replace('https://', '')
old_ip = proxy_address.split(':')[0]
print('old IP : ', old_ip)
dao.plus_proxy_faild_time(old_ip)
def get_proxies(self):
# 加载 Log 配置
get_log_config()
proxy_model_list = []
print('正在爬取西刺代理……')
response = super(XiciSpider, self).get_proxies()
selector = etree.HTML(response.text)
infos = selector.xpath('//tr[@class="odd"]')
for i, info in enumerate(infos):
try:
ip = info.xpath('./td[2]/text()')[0] # ip
port = info.xpath('./td[3]/text()')[0] # 端口
anonymity = info.xpath('./td[5]/text()')[0] # 匿名度
http_type = info.xpath('./td[6]/text()')[0] # 类型
area = info.xpath('./td[4]/a/text()')[0] # 地区
speed = info.xpath('./td[7]/div/@title')[0] # 速度
survival_time = info.xpath('./td[9]/text()')[0] # 存活时间
print(ip + " | " + port + " | " + anonymity + " | " + http_type + " | " + area + " | " + speed + " | " + survival_time)
proxy = Proxy()
proxy.set_ip(ip)
proxy.set_port(port)
proxy.set_http_type(http_type)
proxy.set_anonymity(anonymity)
# 处理空地区
if area is None:
proxy.set_area('')
else:
proxy.set_area(area)
proxy.set_speed(speed)
proxy.set_agent(self.agent)
proxy.set_survival_time(survival_time)
proxy_model_list.append(proxy)
except Exception as e:
logging.debug(e)
logging.debug("抓取 " + self.agent + " 网站共计 " + str(len(proxy_model_list)) + " 个代理")
return proxy_model_list
def get_proxies(self):
get_log_config()
proxy_model_list = []
print('正在爬取西刺代理......')
response = super(XiciSpider, self).get_proxies()
selector = etree.HTML(response.text)
infos = selector.xpath('//tr[@class="odd"]')
for i, info in enumerate(infos):
try:
ip = info.xpath('./td[2]/text()')[0]
port = info.xpath('./td[3]/text()')[0]
anonymity = info.xpath('./td[5]/text()')[0]
http_type = info.xpath('./td[6]/text()')[0]
area = info.xpath('./td[4]/a/text()')[0]
speed = info.xpath('./td[7]/div/@title')[0]
survival_time = info.xpath('./td[9]/text()')[0]
print(ip + " | " + port + " | " + anonymity + " | " +
http_type + " | " + area + " | " + speed + " | " +
survival_time)
proxy = Proxy()
proxy.set_ip(ip)
proxy.set_port(port)
proxy.set_http_type(http_type)
proxy.set_anonymity(anonymity)
if area is None:
proxy.set_area("")
else:
proxy.set_area(area)
proxy.set_speed(speed)
proxy.set_agent(self.agent)
proxy.set_survival_time(survival_time)
proxy_model_list.append(proxy)
print(len(proxy_model_list))
except Exception as e:
logging.debug(e)
logging.debug(f"抓取 {self.agent} 网站共计 {len(proxy_model_list)} 个代理")
return proxy_model_list
def get_proxies(self):
# 加载 Log 配置
get_log_config()
proxy_model_list = []
print('正在爬取ip181……')
response = super(Ip181Spider, self).get_proxies()
# 这个网站的编码是 gb2312
response.encoding = 'gb2312'
selector = etree.HTML(response.text)
infos = selector.xpath('//div[@class="col-md-12"]/table/tbody/tr')
for i, info in enumerate(infos):
try:
ip = info.xpath('./td[1]/text()')[0] # ip
port = info.xpath('./td[2]/text()')[0] # 端口
anonymity = info.xpath('./td[3]/text()')[0] # 匿名度
http_type = info.xpath('./td[4]/text()')[0] # 类型
speed = info.xpath('./td[5]/text()')[0] # 速度
area = info.xpath('./td[6]/text()')[0] # 地区
# print(ip + " | " + port + " | " + anonymity + " | " + http_type + " | " + speed + " | " + area)
if i == 1:
# 把标题过滤掉
pass
else:
proxy = Proxy()
proxy.set_ip(ip)
proxy.set_port(port)
if http_type == 'HTTP,HTTPS':
proxy.set_http_type('http')
else:
proxy.set_http_type(http_type.lower())
proxy.set_anonymity(anonymity)
proxy.set_area(area)
proxy.set_speed(speed)
proxy.set_agent(self.agent)
proxy.set_survival_time("")
proxy_model_list.append(proxy)
except Exception as e:
logging.debug(e)
logging.debug("抓取 " + self.agent + " 网站共计 " +
str(len(proxy_model_list)) + " 个代理")
return proxy_model_list