fix(plugins): fpw parsers for JSON API, mirrors, and looser HTML
- fpw_proxy_list_download: parse JSON list/proxies bodies; jsDelivr monosans tier; crawl timeout 300s - fpw_socks_ssl: try parse_html_table before regex - fpw_hidemy: loose row scan when fixed columns fail - fpw_proxynova: plain IP/port row fallback - fpw_spys_one: HTTPS endpoints; crawl timeout 180s - fpw_gatherproxy: HTTPS + extra JSON key patterns - fpw_checkerproxy: lower min HTML length for parse - fpw_premproxy: ip:port regex fallback when few table rows Made-with: Cursor
This commit is contained in:
@@ -26,7 +26,7 @@ class FpwSocksSslProxyPlugin(BaseHTTPPlugin):
|
||||
def _parse_page(self, html: str, default_protocol: str) -> List[ProxyRaw]:
|
||||
results = []
|
||||
pattern = re.compile(
|
||||
r"(\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3})</td>\s*<td[^>]*>\s*(\d+)",
|
||||
r"(\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3})</td>\s*<td[^>]*>\s*(\d{1,5})",
|
||||
re.I,
|
||||
)
|
||||
for ip, port in pattern.findall(html):
|
||||
@@ -47,7 +47,11 @@ class FpwSocksSslProxyPlugin(BaseHTTPPlugin):
|
||||
proto = "socks4"
|
||||
else:
|
||||
proto = "http"
|
||||
batch = self._parse_page(html, proto)
|
||||
batch = self.parse_html_table(
|
||||
html, column_map={"ip": 0, "port": 1}, protocol=proto
|
||||
)
|
||||
if not batch:
|
||||
batch = self._parse_page(html, proto)
|
||||
results.extend(batch)
|
||||
if batch:
|
||||
logger.info(f"{self.display_name} {url}: {len(batch)} 条")
|
||||
|
||||
Reference in New Issue
Block a user