def run(self):
spider_start_time = str(datetime.now()).split('.')[0]
print spider_start_time, 'time to spider start!'
proxy_manager = ProxyManager()
page = get_html(BASE_URL)
page = unicode(page,'GBK').encode('UTF-8')
page_count = self.get_page_count(page)
page_count_time = str(datetime.now()).split('.')[0]
print page_count_time, 'get page count:', page_count
default_ip = get_default_ip()
if page_count != 0:
last_proxy = None
for i in xrange(1, page_count):
page = get_html(URL_HEADER + str(i) + URL_END, last_proxy)
proxy_list = filte(page)
for proxy in proxy_list:
if proxy.anonymous_type == '高匿':
check_result = check_anonymous(proxy, default_ip)
spider_time = str(datetime.now()).split('.')[0]
if check_result[0]:
proxy.delay_time = check_result[1]
proxy.created_time = str(datetime.now()).split('.')[0]
proxy.is_in_china = 2
proxy_manager.add_proxy(proxy, spider_time)
last_proxy = proxy
else:
pass
def run(self):
spider_start_time = str(datetime.now()).split('.')[0]
print spider_start_time, 'time to spider start!'
proxy_manager = ProxyManager()
last_proxy = None
for url in self.urls:
page = get_html(url)
page_count = self.get_page_count(page)
page_count_time = str(datetime.now()).split('.')[0]
print page_count_time, 'get page count:', page_count
default_ip = get_default_ip()
for i in xrange(1, page_count):
page = get_html(url + str(i))
proxy_list = filte(page)
for proxy in proxy_list:
if proxy.anonymous_type == '高匿':
check_result = check_anonymous(proxy, default_ip)
spider_time = str(datetime.now()).split('.')[0]
if check_result[0]:
proxy.delay_time = check_result[1]
proxy.created_time = str(datetime.now()).split('.')[0]
proxy.is_in_china = 0
if url.endswith(CHINA_ANONYMOUS) or url.endswith(CHINA_NORMAL):
proxy.is_in_china = 1
proxy_manager.add_proxy(proxy, spider_time)
last_proxy = proxy
else:
pass
def run(self):
spider_start_time = str(datetime.now()).split('.')[0]
print spider_start_time, 'time to spider start!'
proxy_manager = ProxyManager()
page = get_html(BASE_URL)
page = unicode(page, 'GBK').encode('UTF-8')
page_count = self.get_page_count(page)
page_count_time = str(datetime.now()).split('.')[0]
print page_count_time, 'get page count:', page_count
default_ip = get_default_ip()
if page_count != 0:
last_proxy = None
for i in xrange(1, page_count):
page = get_html(URL_HEADER + str(i) + URL_END, last_proxy)
proxy_list = filte(page)
for proxy in proxy_list:
if proxy.anonymous_type == '高匿':
check_result = check_anonymous(proxy, default_ip)
spider_time = str(datetime.now()).split('.')[0]
if check_result[0]:
proxy.delay_time = check_result[1]
proxy.created_time = str(
datetime.now()).split('.')[0]
proxy.is_in_china = 2
proxy_manager.add_proxy(proxy, spider_time)
last_proxy = proxy
else:
pass
def run(self):
spider_start_time = str(datetime.now()).split('.')[0]
print spider_start_time, 'time to spider start!'
proxy_manager = ProxyManager()
last_proxy = None
for url in self.urls:
page = get_html(url)
page_count = self.get_page_count(page)
page_count_time = str(datetime.now()).split('.')[0]
print page_count_time, 'get page count:', page_count
default_ip = get_default_ip()
for i in xrange(1, page_count):
page = get_html(url + str(i))
proxy_list = filte(page)
for proxy in proxy_list:
if proxy.anonymous_type == '高匿':
check_result = check_anonymous(proxy, default_ip)
spider_time = str(datetime.now()).split('.')[0]
if check_result[0]:
proxy.delay_time = check_result[1]
proxy.created_time = str(
datetime.now()).split('.')[0]
proxy.is_in_china = 0
if url.endswith(CHINA_ANONYMOUS) or url.endswith(
CHINA_NORMAL):
proxy.is_in_china = 1
proxy_manager.add_proxy(proxy, spider_time)
last_proxy = proxy
else:
pass
