Free proxies that actually work: scrapes HTTP/SOCKS4/SOCKS5 proxies from 700+ sources, verifies every hit (honeypots, HTTPS, anonymity) and learns which sources are worth it. Live list every 6 h.
翻譯準備中
正在載入完整 README。 以下為已儲存的摘錄。
Most free proxy lists are 95 % dead, and a good part of the rest are honeypots or proxies that inject scripts into your pages. proxy-scraper collects public HTTP, SOCKS4 and SOCKS5 proxies from 700+ sources and keeps only the ones that pass every check. It learns with every run which sources are worth it, and it can turn the result into a single rotating proxy.
• Install
• Live proxy list
• Features · Why not just download a list?
• Examples
• Recipes
• Rotating proxy server
• Discord bot
• How it works
• Output
• Options
• GitHub Actions
• FAQ
• Roadmap · Contributing · Acknowledgements檢視完整 README ↗Free HTTP, SOCKS4 and SOCKS5 proxy lists, rebuilt about every hour. A proxy is listed only if it passed the checks of that run, and the result of every check is published with it.
English · 简体中文 · Español · Deutsch · Русский · Português (Brasil) · Français
Website · Benchmark · All lists · Install · Python API · For AI agents · Proxy server · Discord bot · All docs
https://proxy-scraper.de/all.txt
https://proxy-scraper.de/http.txt
https://proxy-scraper.de/socks4.txt
https://proxy-scraper.de/socks5.txt
http.txt, socks4.txt and socks5.txt hold one ip:port per line, all.txt one type://ip:port. Best first, so head -n 20 gives you the best ones. No signup, no API key, CORS headers included. The badges above are the counts of the last run. The same files are on the proxy-list branch, on jsDelivr and in a repository of their own, free-proxy-list. HTTPS-only, elite, stable, per country, per site, JSON and CSV: every list.
Check them from your own network before you use them. No install needed, uvx comes with uv (pipx run does the same):
uvx proxy-scraper-cli --pick 3 --verify # up to 3 proxies from the hourly list that pass right now, from your network
Most free proxy lists on GitHub are long, and most of their entries fail when they are checked. This list is shorter because each run publishes only the proxies that passed. The benchmark runs the same checks on the popular lists every hour and shows what share of each one passes:
Redrawn about every hour from the hourly runs on a GitHub Actions runner. The date is in the chart. The benchmark page has the counts behind each share, how they are measured and why proxy-scraper's own list isn't in it.
What a proxy on the list has passed, in the last run, from that runner:
| Check | What runs | Required for the list |
|---|---|---|
basic | A handshake (HTTP, SOCKS4 or SOCKS5) and a first request that returns a public exit IP that isn't ours | yes |
confirm | A second request to an unrelated site, which has to see the same exit IP | yes |
content | A static test page over plain HTTP that has to arrive byte for byte as fetched directly | yes |
https | A tunnel to port 443 of one test host with a TLS handshake that verifies | no, recorded per proxy (https.txt has the ones that passed) |
Each check ends as passed, failed, unavailable or skipped, with a reason code, the target and the time, in proxies.json, in the CSV and in the tool's output. A check that didn't run is never shown as passed. Details: check states.
What a pass doesn't tell you. Free proxies are run by strangers. Of one run's list, about a quarter was on the list again 24 runs later (median of the week ending 13 Oct 2026). A pass is one measurement, from one network, against test targets: it is not a promise for the next hour or for the site you care about. The HTTPS check is a verified TLS connection to one test host, not a security rating. Use free proxies for public data and testing, never for logins, payments or anything personal. → What the numbers show and what they don't · Why free proxies fail · How it compares · Who runs free proxies
Used by: the hourly list is a built-in source of monosans/proxy-scraper-checker and gfpcom/free-proxy-list.
About every hour GitHub Actions runs proxy-scraper and publishes the hits to the proxy-list branch – every entry passed the first request, the second request and the content check in the last run (the HTTPS test is recorded per entry, not required), best first: fast ones that are likely to still be up come on top.
以上為 README 的開頭部分。其餘內容請閱讀原文。 檢視完整 README ↗