ð·ïž The BEST Web Scraping framework that handles everything from a single request to a full-scale crawl! Don't be shy, join here: https://discord.gg/EMgGbDceNQ and follow here for daily tips and tricks: https://x.com/Scrapling_dev
title: "Scrapling MCP ãµãŒããŒã® API ãªãã¡ã¬ã³ã¹" description: "HTTP ãšãã©ãŠã¶ã«ããããŒã¿æœåºã«äœ¿ã MCP ããŒã«ãšããªã¯ãšã¹ãã»ã¬ã¹ãã³ã¹ã»ã»ãã·ã§ã³ã®ã¢ãã«ã確èªããŸãã"
MCP ãµãŒããŒã®ãªãã¡ã¬ã³ã¹ {#mcp-server-api-reference}
Scrapling MCP ãµãŒããŒã¯ãModel Context ProtocolïŒMCPïŒãéããŠãããŒã¿æœåºãšãã©ãŠã¶æäœã®ããã® 16 åã®ããŒã«ãæäŸããŸããAI ã¢ã·ã¹ã¿ã³ãããšãŒãžã§ã³ãã«æ¥ç¶ãããšãäŒè©±ãéããŠããŒã¿ãæœåºã§ããŸãããããæ€åºãé¿ããæ©èœã䜿ããŸãã
次ã®ã³ãã³ãã§ MCP ãµãŒããŒãèµ·åããŸãã
scrapling mcp
ãµãŒããŒã¯ã©ã¹ãçŽæ¥ã€ã³ããŒãããããšãã§ããŸãã
from scrapling.core.ai import ScraplingMCPServer
server = ScraplingMCPServer()
server.serve(http=False, host="127.0.0.1", port=8000)
ç¬èªã® Chromium äºæãã©ãŠã¶ã䜿ãå Žåã¯ãexecutable_path ãæå®ããŸãã
server = ScraplingMCPServer(executable_path="/path/to/chromium")
ã¬ã¹ãã³ã¹ã¢ãã« {#response-model}
ããŒãžååŸãš HTTP ãªã¯ãšã¹ãã®ããŒã«ã¯ã次ã®åœ¢åŒã§ 1 åã®åŒã³åºãã«ã€ã 1 ä»¶ã®ã¬ã¹ãã³ã¹ãè¿ããŸããã»ãã·ã§ã³ç®¡çã®ããŒã«ã¯ãåŸã«ç€ºãã¢ãã«ã䜿ããŸããbrowser_screenshot ã¯ããŒãžãŸãã¯èŠçŽ ã®ç»åãšçŸåšã® URL ããç»åãããã¯ãšããã¹ããããã¯ã§è¿ããŸããbrowser_extract ãš browser_actions ã¯éåžžã®ããã¹ããè¿ããŸãã2 ã€ã®ãããã¯ãŒã¯ããŒã«ã¯ãåŸã«ç€ºãã¢ãã«ã§æ§é åããã JSON ãè¿ããŸããbrowser_evaluate ã¯çµæã JSON ã«ããŠãããã¹ããããã¯ã§è¿ããŸãã
::: scrapling.core.ai.server.ResponseModel
handler: python
:docstring:
ãããã¯ãŒã¯ãªã¯ãšã¹ãã®ã¢ãã« {#network-request-models}
browser_network_requests 㯠NetworkRequestsModel ãè¿ããrequestsãnext_cursorãhas_moreãdropped_count ãå«ã¿ãŸããå NetworkRequestInfo ã«ã¯ idãurlãmethodãresource_typeãstatus ããããŸããç¶ããååŸããã«ã¯ãnext_cursor ã after_id ãšããŠæž¡ããŸããhas_more ã¯ãçŸåšã®å±¥æŽã«ãŸã äžèŽããçµæããããã瀺ããŸãã
browser_network_request 㯠NetworkRequestModel ãè¿ããrequest_idãpartãdataãnote ãå«ã¿ãŸããæŠèŠãšããããŒã¯ãªããžã§ã¯ãã§ããä¿åãããæ¬æå
šäœã¯ãå
容ã JSON ã§ãæååã§è¿ããŸããnote ã¯ãæ¬æããªãå ŽåãããããŒãäžå®å
šãªå Žåã®èª¬æã§ãã
::: scrapling.core.ai._network_formatting.NetworkRequestInfo
handler: python
:docstring:
::: scrapling.core.ai.server.NetworkRequestsModel
handler: python
:docstring:
::: scrapling.core.ai._network_formatting.NetworkRequestModel
handler: python
:docstring:
ã»ãã·ã§ã³ã¢ãã« {#session-models}
ã»ãã·ã§ã³ç®¡çã«äœ¿ãã¢ãã«ã¯ã©ã¹ã§ãã
::: scrapling.core.ai.server.SessionInfo
handler: python
:docstring:
::: scrapling.core.ai.server.SessionCreatedModel
handler: python
:docstring:
::: scrapling.core.ai.server.SessionClosedModel
handler: python
:docstring:
MCP ãµãŒããŒã¯ã©ã¹ {#mcp-server-class}
MCP ãµãŒããŒã®ã¡ã€ã³ã¯ã©ã¹ã¯ã次ã®ããŒã«ãæäŸããŸãã
make_requestïŒãã©ãŠã¶ãæš¡å£ãã HTTP ãªã¯ãšã¹ãã§ 1 ã€ã® URL ãååŸããã¯ã©ã€ã¢ã³ããèªåã§éããŸããGETãPOSTãPUTãDELETE ã«å¯Ÿå¿ããŸããbrowser_fetch_onceïŒã¹ãã«ã¹ãã©ãŠã¶ã§ 1 ã€ã® URL ãååŸããJavaScript ã®å®è¡ãš Cloudflare æ€èšŒã®åŠçãè¡ã£ãŠãããã©ãŠã¶ãéããŸãããã®åŸãããŒãžãæäœãããããããã¯ãŒã¯å±¥æŽã確èªãããããå Žåã¯ãæ°žç¶ã»ãã·ã§ã³ã䜿ã£ãŠãã ãããbrowser_extractïŒçŸåšã®ããŒãžãèŠçŽ ããAI åãã®æ§é åãããã¹ãããã·ã§ãããHTMLãMarkdownãããã¹ããšããŠèªã¿åããŸããåèªã¿èŸŒã¿ã¯äžèŠã§ããã©ãŒã ãæäœã®çµæãä¿ã¡ãŸããã¹ãããã·ã§ããã«ã¯èŠçŽ ã®åœ¹å²ãååãåç §ãäœçœ®ããµã€ãºãå«ãŸããŸããæ£èŠè¡šçŸã®æ€çŽ¢ã§ã¯ãäžèŽããè¡ãšãã®ååŸã®å 容ã芪ããŒããè¿ããŸããbrowser_actionsïŒããŠã¹ã®ç§»åããããŒãã¯ãªãã¯ãã¹ã¯ããŒã«ããã©ãŒã å ¥åãããŒæäœããã€ã¢ãã°ãžã®å¿çãåŸ æ©ã 1 åã®åŒã³åºãã«ãŸãšããŸããéç¥ã確èªãåãå ¥ãããéããããšãã§ããå ¥åãã€ã¢ãã°ã«ã¯æåãå ¥åã§ããŸããæ€çŽ¢æ¬ã«å ¥åããŠéä¿¡ããåŸ ã£ãŠããçµæãéãæäœããæ®µéããšã«åŒã³åºããã«å®è¡ã§ããŸããç§»åãšã¯ãªãã¯ã«ã¯ãã»ã¬ã¯ã¿ãŒãã¹ãããã·ã§ããã®åç §ã座æšãæå®ã§ããŸããèŠçŽ ãåŸ ã¡ã衚瀺é åãŸã§ã¹ã¯ããŒã«ããŸããæ®µéçãªç§»åãå·Šã»å³ã»äžå€®ã¯ãªãã¯ãããã«ã¯ãªãã¯ãå ¥ãåã®é åå ã®ã¹ã¯ããŒã«ã«å¯Ÿå¿ããŸãã
ã»ã¬ã¯ã¿ãŒãã¹ãããã·ã§ããã®åç §ã§å ¥åæ¬ãéžã³ãŸããæåã®å ¥åããã§ãã¯ããã¯ã¹ã®ãªã³ãšãªããã©ãžãªãã¿ã³ã®éžæãæšæºã®éžæãªã¹ãã®ã©ãã«ã«ããåäžã»è€æ°éžæãã§ããŸããæåã®çœ®ãæããæ¶å»ãã«ãŒãœã«äœçœ®ããã®è¿œå å ¥åãã§ããŸããããŒæäœã¯çŸåšãã©ãŒã«ã¹ãããå Žæã«äœçšããŸããäœéã¢ãŒãã§ã¯ãæåãæäœã®éã«ã©ã³ãã ãªåŸ ã¡æéãå ¥ããŸãã
ã»ã¬ã¯ã¿ãŒãã¹ãããã·ã§ããã®åç §ã§ãã³ã³ãã³ããèªã¿èŸŒã¿äžã®ãªãŒããŒã¬ã€ãæå®ããç¶æ ã«ãªããŸã§åŸ ãŠãŸããèªã¿èŸŒã¿ã€ãã³ãããããã¯ãŒã¯ã®éä¿¡ãèœã¡çããŸã§ã®åŸ æ©ãæå®æéã®åŸ æ©ã䜿ããŸãã
browser_evaluateïŒçŸåšã®ããŒãžã§ JavaScript ãå®è¡ããç¬èªã®ããŒã¿æœåºãèšç®ãã¢ããªã®ç¶æ 確èªãå 容ã®å€æŽãè¡ããŸããéåæã¹ã¯ãªããã«å¯Ÿå¿ããçµæã JSON ã§è¿ããŸããbrowser_network_requestsïŒã¿ããããŒãžç§»åãæäœããŸããã§ãå®äºãããã©ãŠã¶ãªã¯ãšã¹ããæ€çŽ¢ããŸããä¿åããã API åŒã³åºããHTTP ãšã©ãŒããªãã€ã¬ã¯ããæ¢ããŸããéçãªãœãŒã¹ã¯æ¢å®ã§é衚瀺ã«ããŠãäžèŠãªçµæãæžãããŸãã倱æãããªã¯ãšã¹ããæªå®äºã®ãªã¯ãšã¹ãã¯å«ã¿ãŸãããããŒãžåå²ã«å¯Ÿå¿ããæ§é åããŒã¿ãè¿ããŸããbrowser_network_requestïŒä¿åæžã¿ãªã¯ãšã¹ãã®æŠèŠãããããŒãéä¿¡ããŒã¿ãæ¬æãæ§é åããã JSON ã§èªã¿åããŸããåéä¿¡ãããéžãã éšåãçç¥ããã«è¿ããŸãã4xx ã 5xx ã® HTTP ã¬ã¹ãã³ã¹ãå«ããä¿åæžã¿ã¬ã¹ãã³ã¹ã¯ããŒãžç§»ååŸãèªããŸããèšé²ãå®äºãããã®ã ããå±¥æŽã«çŸããŸããå±¥æŽã®èªã¿åããã»ãã·ã§ã³ã®çµäºã¯ãé²è¡äžã®èšé²ãåŸ ã¡ãŸãããæªå®äºã®èšé²ã¯ããŒãžç§»åãçµäºæã«å€±ãããããšããããŸãããã€ãå㯠Playwright ããååŸããããããµãŒããŒãéä¿¡ããçã®ãã€ãåãšç°ãªãå ŽåããããŸããä¿åãããã€ãåãæå¹ãª UTF-8 ãªããPlaywright ãšåãæ¹æ³ã§ããã¹ãã«å€æããŸãããã以å€ã§ã¯ã宣èšãããæåã³ãŒãã䜿ããŸããæ¬æãèªã¿åã£ãŠä¿åããã®ã¯ã察å¿ããããã¹ã圢åŒã®Content-Typeã ãã§ãããã€ããªãçš®é¡ãäžæãªãã®ãçš®é¡ãæå®ãããŠããªããã®ã¯ãæ¬æãèªãŸãã«ã¡ã¿ããŒã¿ãšããããŒã ããä¿åããŸããããŒãžã®èªã¿èŸŒã¿æ¹ã¯å€ãããŸãããå±¥æŽã«ã¯ãµã€ãºäžéããããŸããæ¬æãããã¹ãã§ãªãã倧ãããããèªããªãå Žåãªã©ã¯ãè£è¶³æ å ±ã§çç±ã瀺ããŸããå¿ èŠãªããŒã¿ã¯ MCP ã»ãã·ã§ã³ãéããåã«èªãã§ãã ãããbrowser_fetchïŒéããŠããã¹ãã«ã¹ãã©ãŠã¶ã»ãã·ã§ã³ã§ããŒãžãååŸããHTMLãMarkdownãããã¹ããã¹ãããã·ã§ãããæœåºããŸããã¹ãããã·ã§ããã¯ããŒãžå šäœãŸãã¯æå®ããèŠçŽ ã察象ã«ããåŸã®æäœã§äœ¿ãåç §ãäœçœ®ããµã€ãºãå«ã¿ãŸãã
::: scrapling.core.ai.server.ScraplingMCPServer
handler: python
:docstring: