참고소스 수정본
This commit is contained in:
LASTA_DEV01\lasta
153
참고/firecrawl-main/apps/test-suite/data/crawl.json
Normal file
153
참고/firecrawl-main/apps/test-suite/data/crawl.json
Normal file
@@ -0,0 +1,153 @@
|
||||
[
|
||||
{
|
||||
"website": "https://www.vellum.ai/llm-leaderboard",
|
||||
"expected_min_num_of_pages": 1,
|
||||
"expected_crawled_pages": ["https://www.vellum.ai/llm-leaderboard"]
|
||||
},
|
||||
{
|
||||
"website": "https://openai.com/news",
|
||||
"expected_min_num_of_pages": 4,
|
||||
"expected_crawled_pages": [
|
||||
"https://openai.com/news/company/",
|
||||
"https://openai.com/news/research/",
|
||||
"https://openai.com/news/safety-and-alignment/",
|
||||
"https://openai.com/news/stories/"
|
||||
]
|
||||
},
|
||||
{
|
||||
"website": "https://www.framer.com/pricing",
|
||||
"expected_min_num_of_pages": 1,
|
||||
"expected_not_crawled_pages": [
|
||||
"https://www.framer.com/features/navigation/",
|
||||
"https://www.framer.com/contact/",
|
||||
"https://www.framer.com/add-ons/",
|
||||
"https://www.framer.com/free-saas-ui-kit/",
|
||||
"https://www.framer.com/help/",
|
||||
"https://www.framer.com/features/effects/",
|
||||
"https://www.framer.com/enterprise/",
|
||||
"https://www.framer.com/templates/"
|
||||
]
|
||||
},
|
||||
{
|
||||
"website": "https://mendable.ai/pricing",
|
||||
"expected_min_num_of_pages": 1,
|
||||
"expected_not_crawled_pages": [
|
||||
"https://mendable.ai/",
|
||||
"https://mendable.ai/blog",
|
||||
"https://mendable.ai/signin",
|
||||
"https://mendable.ai/signup",
|
||||
"https://mendable.ai",
|
||||
"https://mendable.ai/usecases/sales-enablement",
|
||||
"https://mendable.ai/usecases/documentation",
|
||||
"https://mendable.ai/usecases/cs-enablement",
|
||||
"https://mendable.ai/usecases/productcopilot",
|
||||
"https://mendable.ai/security"
|
||||
],
|
||||
"notes": "This one should not go backwards, but it does!"
|
||||
},
|
||||
{
|
||||
"website": "https://agentops.ai/blog",
|
||||
"expected_min_num_of_pages": 6,
|
||||
"expected_crawled_pages": [
|
||||
"https://www.agentops.ai/blog/effortless-hr-management-with-saas",
|
||||
"https://www.agentops.ai/blog/streamlining-hr-with-saas",
|
||||
"https://www.agentops.ai/blog/simplify-hr-with-modern-saas-solutions",
|
||||
"https://www.agentops.ai/blog/efficient-hr-operations-with-saas",
|
||||
"https://www.agentops.ai/blog/hr-made-simple-with-saas",
|
||||
"https://agentops.ai/blog"
|
||||
],
|
||||
"expected_not_crawled_pages": [
|
||||
"https://agentops.ai/about-us",
|
||||
"https://agentops.ai/contact-us"
|
||||
]
|
||||
},
|
||||
{
|
||||
"website": "https://en.wikipedia.org/wiki/T._N._Seshan",
|
||||
"expected_min_num_of_pages": 1,
|
||||
"expected_not_crawled_pages": [
|
||||
"https://en.wikipedia.org/wiki/Wikipedia:Contents",
|
||||
"https://en.wikipedia.org/wiki/Wikipedia:Contact_us",
|
||||
"https://en.wikipedia.org/wiki/V._S._Ramadevi",
|
||||
"https://en.wikipedia.org/wiki/Wikipedia:About",
|
||||
"https://en.wikipedia.org/wiki/Help:Introduction",
|
||||
"https://en.wikipedia.org/wiki/H._D._Deve_Gowda",
|
||||
"https://en.wikipedia.org/wiki/File:T.N._Seshan_in_1994.jpg"
|
||||
]
|
||||
},
|
||||
|
||||
{
|
||||
"website": "https://ycombinator.com/companies",
|
||||
"expected_min_num_of_pages": 20,
|
||||
"expected_crawled_pages": [
|
||||
"https://www.ycombinator.com/companies/industry/elearning",
|
||||
"https://www.ycombinator.com/companies/industry/computer-vision",
|
||||
"https://www.ycombinator.com/companies/industry/health-tech",
|
||||
"https://www.ycombinator.com/companies/industry/education",
|
||||
"https://www.ycombinator.com/companies/industry/robotics",
|
||||
"https://www.ycombinator.com/companies/industry/hardware",
|
||||
"https://www.ycombinator.com/companies/industry/saas",
|
||||
"https://www.ycombinator.com/companies/industry/hard-tech",
|
||||
"https://www.ycombinator.com/companies/industry/developer-tools",
|
||||
"https://www.ycombinator.com/companies/industry/entertainment",
|
||||
"https://www.ycombinator.com/companies/industry/finance",
|
||||
"https://www.ycombinator.com/companies/industry/generative-ai",
|
||||
"https://www.ycombinator.com/companies/industry/machine-learning"
|
||||
]
|
||||
},
|
||||
{
|
||||
"website": "https://firecrawl.dev",
|
||||
"expected_min_num_of_pages": 2,
|
||||
"expected_crawled_pages": [
|
||||
"https://www.firecrawl.dev/",
|
||||
"https://www.firecrawl.dev/pricing"
|
||||
]
|
||||
},
|
||||
{
|
||||
"website": "https://fly.io/docs/gpus/gpu-quickstart",
|
||||
"expected_min_num_of_pages": 1,
|
||||
"expected_not_crawled_pages": [
|
||||
"https://fly.io/docs/getting-started/",
|
||||
"https://fly.io/docs/hands-on/",
|
||||
"https://fly.io/docs/about/support/",
|
||||
"https://fly.io/docs/blueprints/going-to-production-with-healthcare-apps/",
|
||||
"https://fly.io/docs/machines/flyctl/fly-machine-update/",
|
||||
"https://fly.io/docs/blueprints/review-apps-guide/",
|
||||
"https://fly.io/docs/blueprints/supercronic/"
|
||||
],
|
||||
"notes": "This one should not go backwards, but it does!"
|
||||
},
|
||||
{
|
||||
"website": "https://www.instructables.com/circuits",
|
||||
"expected_min_num_of_pages": 12,
|
||||
"expected_crawled_pages": [
|
||||
"https://www.instructables.com/circuits/",
|
||||
"https://www.instructables.com/circuits/apple/projects/",
|
||||
"https://www.instructables.com/circuits/art/projects/",
|
||||
"https://www.instructables.com/circuits/electronics/projects/",
|
||||
"https://www.instructables.com/circuits/microsoft/projects/",
|
||||
"https://www.instructables.com/circuits/microcontrollers/projects/",
|
||||
"https://www.instructables.com/circuits/community/",
|
||||
"https://www.instructables.com/circuits/leds/projects/",
|
||||
"https://www.instructables.com/circuits/gadgets/projects/",
|
||||
"https://www.instructables.com/circuits/arduino/projects/",
|
||||
"https://www.instructables.com/circuits/lasers/projects/",
|
||||
"https://www.instructables.com/circuits/clocks/projects/"
|
||||
]
|
||||
},
|
||||
{
|
||||
"website": "https://richmondconfidential.org",
|
||||
"expected_min_num_of_pages": 20,
|
||||
"expected_crawled_pages": [
|
||||
"https://richmondconfidential.org/2009/10/13/salesians-star-guard-has-a-big-impact/",
|
||||
"https://richmondconfidential.org/2009/10/13/on-team-of-beginners-oilers-old-hand-stands-out/",
|
||||
"https://richmondconfidential.org/2009/10/19/point-richmond-clockmaker-turns-clutter-into-crafts/",
|
||||
"https://richmondconfidential.org/2009/10/13/profile-maurice-cathy/",
|
||||
"https://richmondconfidential.org/2009/10/13/soul-food-rescue-mission-rebuilds-diets-and-lives/",
|
||||
"https://richmondconfidential.org/2009/10/21/in-tough-economy-pain-trickles-to-the-bottom/",
|
||||
"https://richmondconfidential.org/2009/10/19/richmond-homicide-map/",
|
||||
"https://richmondconfidential.org/2009/10/13/rough-roads-for-richmonds-cab-drivers/",
|
||||
"https://richmondconfidential.org/2009/10/13/before-napa-there-was-winehaven/",
|
||||
"https://richmondconfidential.org/2009/10/13/family-calls-for-end-to-violence-at-memorial-for-slain-woman-friend/"
|
||||
]
|
||||
}
|
||||
]
|
||||
118
참고/firecrawl-main/apps/test-suite/data/scrape.json
Normal file
118
참고/firecrawl-main/apps/test-suite/data/scrape.json
Normal file
@@ -0,0 +1,118 @@
|
||||
[
|
||||
{
|
||||
"website": "https://www.anthropic.com/claude",
|
||||
"prompt": "Does this website contain pricing information?",
|
||||
"expected_output": "yes"
|
||||
},
|
||||
{
|
||||
"website": "https://mendable.ai/pricing",
|
||||
"prompt": "Does this website contain pricing information?",
|
||||
"expected_output": "yes"
|
||||
},
|
||||
{
|
||||
"website": "https://openai.com/news",
|
||||
"prompt": "Does this website contain a list of research news?",
|
||||
"expected_output": "yes"
|
||||
},
|
||||
{
|
||||
"website": "https://agentops.ai",
|
||||
"prompt": "Does this website contain a code snippets?",
|
||||
"expected_output": "yes"
|
||||
},
|
||||
{
|
||||
"website": "https://ycombinator.com/companies",
|
||||
"prompt": "Does this website contain a list bigger than 5 of ycombinator companies?",
|
||||
"expected_output": "yes"
|
||||
},
|
||||
{
|
||||
"website": "https://firecrawl.dev",
|
||||
"prompt": "Does this website contain a list bigger than 5 of ycombinator companies?",
|
||||
"expected_output": "no"
|
||||
},
|
||||
{
|
||||
"website": "https://en.wikipedia.org/wiki/T._N._Seshan",
|
||||
"prompt": "Does this website talk about Seshan's career?",
|
||||
"expected_output": "yes"
|
||||
},
|
||||
{
|
||||
"website": "https://mendable.ai/blog",
|
||||
"prompt": "Does this website contain multiple blog articles?",
|
||||
"expected_output": "yes"
|
||||
},
|
||||
{
|
||||
"website": "https://www.framer.com/pricing",
|
||||
"prompt": "Is there an enterprise pricing option?",
|
||||
"expected_output": "yes"
|
||||
},
|
||||
{
|
||||
"website": "https://fly.io/docs/gpus/gpu-quickstart",
|
||||
"prompt": "Is there a fly deploy command on this page?",
|
||||
"expected_output": "yes"
|
||||
},
|
||||
{
|
||||
"website": "https://news.ycombinator.com/",
|
||||
"prompt": "Does this website contain a list of articles in a table markdown format?",
|
||||
"expected_output": "yes"
|
||||
},
|
||||
{
|
||||
"website": "https://www.vellum.ai/llm-leaderboard",
|
||||
"prompt": "Does this website contain a model comparison table?",
|
||||
"expected_output": "yes"
|
||||
},
|
||||
{
|
||||
"website": "https://www.bigbadtoystore.com",
|
||||
"prompt": "are there more than 3 toys in the new arrivals section?",
|
||||
"expected_output": "yes"
|
||||
},
|
||||
{
|
||||
"website": "https://www.instructables.com",
|
||||
"prompt": "Does the site offer more than 5 links about circuits?",
|
||||
"expected_output": "yes"
|
||||
},
|
||||
{
|
||||
"website": "https://www.powells.com",
|
||||
"prompt": "is there at least 10 books webpage links?",
|
||||
"expected_output": "yes"
|
||||
},
|
||||
{
|
||||
"website": "https://www.royalacademy.org.uk",
|
||||
"prompt": "is there information on upcoming art exhibitions?",
|
||||
"expected_output": "yes"
|
||||
},
|
||||
{
|
||||
"website": "https://www.eastbaytimes.com",
|
||||
"prompt": "Is there a Trending Nationally section that lists articles?",
|
||||
"expected_output": "yes"
|
||||
},
|
||||
{
|
||||
"website": "https://www.manchestereveningnews.co.uk",
|
||||
"prompt": "is the content focused on Manchester sports news?",
|
||||
"expected_output": "no"
|
||||
},
|
||||
{
|
||||
"website": "https://physicsworld.com",
|
||||
"prompt": "does the site provide at least 15 updates on the latest physics research?",
|
||||
"expected_output": "yes"
|
||||
},
|
||||
{
|
||||
"website": "https://richmondconfidential.org",
|
||||
"prompt": "does the page contains more than 4 articles?",
|
||||
"expected_output": "yes"
|
||||
},
|
||||
{
|
||||
"website": "https://www.techinasia.com",
|
||||
"prompt": "is there at least 10 articles of the startup scene in Asia?",
|
||||
"expected_output": "yes",
|
||||
"notes": "The website has a paywall and bot detectors."
|
||||
},
|
||||
{
|
||||
"website": "https://www.boardgamegeek.com",
|
||||
"prompt": "are there more than 5 board game news?",
|
||||
"expected_output": "yes"
|
||||
},
|
||||
{
|
||||
"website": "https://www.mountainproject.com",
|
||||
"prompt": "Are there more than 3 climbing guides for Arizona?",
|
||||
"expected_output": "yes"
|
||||
}
|
||||
]
|
||||
Reference in New Issue
Block a user