def ip_spider2():
ip = SuperSpider(host='192.168.0.172',
table_name='ip_pool',
field_list=[
'spider_datetime', 'source_name', 'source_page', 'ip',
'address'
])
ip.source_name = '89免费代理'
page = 1
while True:
ip.source_page = f'http://www.89ip.cn/index_{page}.html'
data_list = ip.data_search(f'http://www.89ip.cn/index_{page}.html',
'//table[@class="layui-table"]//td/text()')
if not data_list:
break
print(f'第{page}页')
for i in range(0, 75, 5):
try:
ip_value = data_list[i].strip(' \n\t')
ip_port = data_list[i + 1].strip(' \n\t')
ip.ip = f"http://{ip_value}:{ip_port}"
ip.address = data_list[i + 2].strip(' \n\t')
except:
break
ip.data_save()
print(f'{ip.source_name}-第{page}页-{ip.ip}-导入完成')
page += 1
time.sleep(2)
ip.spider_end()
def ip_spider5():
ip = SuperSpider(host='192.168.0.172',
table_name='ip_pool',
field_list=[
'spider_datetime', 'source_name', 'source_page', 'ip',
'address'
])
ip.source_name = '开心代理'
page = 1
while True:
ip.source_page = f'http://ip.kxdaili.com/ipList/{page}.html#ip'
data_list = ip.data_search(
f'http://ip.kxdaili.com/ipList/{page}.html#ip',
'//table[@class="ui table segment"]//td/text()')
if not data_list:
break
for i in range(0, 70, 7):
ip.address = data_list[i + 5]
h_list = data_list[i + 3].split(',')
for h in h_list:
ip.ip = f'{h.lower()}://{data_list[i]}:{data_list[i+1]}'
ip.data_save()
print(f'{ip.source_name}-第{page}页-{ip.ip}-导入完成')
page += 1
ip.spider_end()
def ip_spider7():
ip = SuperSpider(host='192.168.0.172',
table_name='ip_pool',
field_list=[
'spider_datetime', 'source_name', 'source_page', 'ip',
'address'
])
page_all = ip.data_search('http://www.66ip.cn/index.html',
'//div[@id="PageList"]//a[last()-1]/text()')[0]
for page in range(1, int(page_all) + 1):
data_list = ip.data_search(
f'http://www.66ip.cn/{page}.html',
'//div[@class="containerbox boxindex"]//table//tr//text()',
'gbk')[5:]
for i in range(0, 10000, 5):
try:
ip.ip = f'http://{data_list[i]}:{data_list[i+1]}'
ip.address = data_list[i + 2]
ip.source_name = '66代理'
ip.source_page = f'http://www.66ip.cn/{page}.html'
ip.data_save()
print(f'{ip.source_name}-第{page}页-{ip.ip}-导入完成')
except:
break
ip.spider_end()
def ip_spider4():
ip = SuperSpider(host='192.168.0.172',
table_name='ip_pool',
field_list=[
'spider_datetime', 'source_name', 'source_page', 'ip',
'address'
])
ip.source_name = '方法SEO'
ip.source_page = 'https://ip.seofangfa.com/'
data_list = ip.data_search('https://ip.seofangfa.com/',
'//table[@class="table"]//td/text()')
for i in range(0, 250, 5):
ip.ip = f'http://{data_list[i]}:{data_list[i+1]}'
ip.address = data_list[i + 3]
ip.data_save()
print(f'{ip.source_name}-{ip.ip}-导入完成')
ip.spider_end()
def ip_spider1():
ip = SuperSpider(host='192.168.0.172',
table_name='ip_pool',
field_list=[
'spider_datetime', 'source_name', 'source_page', 'ip',
'address'
])
ip.source_name = '快代理'
for page in range(1, 100):
print(f'第{page}页')
ip.source_page = f'https://www.kuaidaili.com/free/inha/{page}/'
data_list = ip.data_search(
f'https://www.kuaidaili.com/free/inha/{page}/',
'//table[@class="table table-bordered table-striped"]//td/text()')
for i in range(0, 105, 7):
try:
ip.ip = f'http://{data_list[i]}:{data_list[i+1]}'
ip.address = data_list[i + 4]
except:
break
ip.data_save()
print(f'{ip.source_name}-第{page}页-{ip.ip}-导入完成')
time.sleep(10)
ip.spider_end()
