海外爬虫 IP 池

https://github.com/constverum/ProxyBroker/blob/master/proxybroker/providers.py

https://list.proxylistplus.com/SSL-List-1

https://list.proxylistplus.com/Fresh-HTTP-Proxy-List-1

https://cool-proxy.net/
https://github.com/imWildCat/scylla/blob/master/scylla/providers/coolproxyprovider.py

https://free-proxy-list.net/
https://github.com/imWildCat/scylla/blob/master/scylla/providers/freeproxylist_provider.py

https://proxyhttp.net/
https://github.com/imWildCat/scylla/blob/master/scylla/providers/httpproxyprovider.py

https://www.ipaddress.com/proxy-list/
https://github.com/imWildCat/scylla/blob/master/scylla/providers/ipaddress_provider.py

http://proxy-list.org/english/index.php
https://github.com/imWildCat/scylla/blob/master/scylla/providers/proxylistprovider.py

https://raw.githubusercontent.com/sunny9577/proxy-scraper/master/proxies.json
https://github.com/imWildCat/scylla/blob/master/scylla/providers/proxyscraperprovider.py

http://www.proxylists.net/countries.html
https://github.com/imWildCat/scylla/blob/master/scylla/providers/proxylists_provider.py

https://github.com/imWildCat/scylla/blob/master/scylla/providers/proxynova_provider.py

http://pubproxy.com/api/proxy?limit=5&format=txt&type=http&level=anonymous&lastcheck=60&nocountry=CN

https://github.com/imWildCat/scylla/blob/master/scylla/providers/rmccurdy_provider.py

https://github.com/imWildCat/scylla/blob/master/scylla/providers/spysmeprovider.py

https://github.com/imWildCat/scylla/blob/master/scylla/providers/spysoneprovider.py

https://github.com/imWildCat/scylla/blob/master/scylla/providers/thespeedXprovider.py

https://proxy-daily.com/

http://ab57.ru/downloads/proxyold.txt

http://www.proxylists.net/http.txt

http://www.proxylists.net/http_highanon.txt

http://pubproxy.com/api/proxy?limit=5&format=txt&type=http&level=anonymous&lastcheck=60&nocountry=CN
http://pubproxy.com/api/proxy?limit=5&format=txt&type=http&level=anonymous&last_check=60&country=CN

http://free-proxy.cz/zh/proxylist/country/CN/all/ping/all
https://github.com/phpgao/proxypool/blob/master/job/htmlcz.go

http://nntime.com/proxy-updated-01.htm
https://github.com/phpgao/proxypool/blob/master/job/htmlnntime.go

https://premproxy.com/list/time-01.htm
https://github.com/phpgao/proxypool/blob/master/job/htmlpremproxy.go

https://github.com/phpgao/proxypool/blob/master/job/htmlproxydb.go

https://github.com/phpgao/proxypool/blob/master/job/htmlsite_digger.go

https://github.com/phpgao/proxypool/blob/master/job/htmlultraproxies.go

https://github.com/phpgao/proxypool/blob/master/job/htmlus_proxy.go

https://github.com/phpgao/proxypool/blob/master/job/jsoncool_proxy.go

https://github.com/phpgao/proxypool/blob/master/job/realiveproxy.go

https://github.com/phpgao/proxypool/blob/master/job/reblackhat.go

https://github.com/phpgao/proxypool/blob/master/job/redogdev.go

https://github.com/phpgao/proxypool/blob/master/job/refreeip.go

https://github.com/phpgao/proxypool/blob/master/job/rehttptunnel.go

https://github.com/phpgao/proxypool/blob/master/job/remy_proxy.go

https://github.com/phpgao/proxypool/blob/master/job/renewproxy.go

https://github.com/phpgao/proxypool/blob/master/job/reproxyiplist.go

https://github.com/phpgao/proxypool/blob/master/job/reproxylist.go

https://github.com/phpgao/proxypool/blob/master/job/rexseo.go

https://github.com/derekhe/ProxyPool/blob/master/lib/proxybroker/providers.py

https://github.com/Jiramew/spoon/blob/master/spoonserver/proxy/listendeprovider.py

https://github.com/Jiramew/spoon/blob/master/spoonserver/proxy/nordprovider.py

https://github.com/Jiramew/spoon/blob/master/spoonserver/proxy/pdbprovider.py

https://github.com/Jiramew/spoon/blob/master/spoonserver/proxy/plpprovider.py

https://github.com/Jiramew/spoon/blob/master/spoonserver/proxy/premprovider.py

https://github.com/Jiramew/spoon/blob/master/spoonserver/proxy/sslprovider.py

https://github.com/Jiramew/spoon/blob/master/spoonserver/proxy/webprovider.py

https://www.freeproxy.world/

http://proxydb.net/

http://www.xsdaili.cn/

https://github.com/bluet/proxybroker2/blob/master/proxybroker/providers.py

https://github.com/nicksherron/proxi/blob/master/internal/providers.go

# def freeProxy10():
#     """
#     墙外网站 cn-proxy
#     :return:
#     """
#     urls = ['http://cn-proxy.com/', 'http://cn-proxy.com/archives/218']
#     request = WebRequest()
#     for url in urls:
#         r = request.get(url, timeout=10)
#         proxies = re.findall(r'<td>(\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3})</td>[\w\W]<td>(\d+)</td>', r.text)
#         for proxy in proxies:
#             yield ':'.join(proxy)

# @staticmethod
# def freeProxy11():
#     """
#     https://proxy-list.org/english/index.php
#     :return:
#     """
#     urls = ['https://proxy-list.org/english/index.php?p=%s' % n for n in range(1, 10)]
#     request = WebRequest()
#     import base64
#     for url in urls:
#         r = request.get(url, timeout=10)
#         proxies = re.findall(r"Proxy\('(.*?)'\)", r.text)
#         for proxy in proxies:
#             yield base64.b64decode(proxy).decode()

# @staticmethod
# def freeProxy12():
#     urls = ['https://list.proxylistplus.com/Fresh-HTTP-Proxy-List-1']
#     request = WebRequest()
#     for url in urls:
#         r = request.get(url, timeout=10)
#         proxies = re.findall(r'<td>(\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3})</td>[\s\S]*?<td>(\d+)</td>', r.text)
#         for proxy in proxies:
#             yield ':'.join(proxy)

及时获取更新,请关注公众号“爬虫技术学习”(spider-learn)

多年大厂求职&面试官经验,简历付费优化,¥ 500/次。

公众号“爬虫技术学习(spider-learn)”

About 逸飞

后端工程师

发表评论

邮箱地址不会被公开。 必填项已用*标注