Spaces:
Build error
Build error
File size: 11,857 Bytes
a8b3f00 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 |
import datetime
import json
import requests
from flask_login import current_user
from core.helper import encrypter
from core.rag.extractor.firecrawl.firecrawl_app import FirecrawlApp
from extensions.ext_redis import redis_client
from extensions.ext_storage import storage
from services.auth.api_key_auth_service import ApiKeyAuthService
class WebsiteService:
@classmethod
def document_create_args_validate(cls, args: dict):
if "url" not in args or not args["url"]:
raise ValueError("url is required")
if "options" not in args or not args["options"]:
raise ValueError("options is required")
if "limit" not in args["options"] or not args["options"]["limit"]:
raise ValueError("limit is required")
@classmethod
def crawl_url(cls, args: dict) -> dict:
provider = args.get("provider")
url = args.get("url")
options = args.get("options")
credentials = ApiKeyAuthService.get_auth_credentials(current_user.current_tenant_id, "website", provider)
if provider == "firecrawl":
# decrypt api_key
api_key = encrypter.decrypt_token(
tenant_id=current_user.current_tenant_id, token=credentials.get("config").get("api_key")
)
firecrawl_app = FirecrawlApp(api_key=api_key, base_url=credentials.get("config").get("base_url", None))
crawl_sub_pages = options.get("crawl_sub_pages", False)
only_main_content = options.get("only_main_content", False)
if not crawl_sub_pages:
params = {
"crawlerOptions": {
"includes": [],
"excludes": [],
"generateImgAltText": True,
"limit": 1,
"returnOnlyUrls": False,
"pageOptions": {"onlyMainContent": only_main_content, "includeHtml": False},
}
}
else:
includes = options.get("includes").split(",") if options.get("includes") else []
excludes = options.get("excludes").split(",") if options.get("excludes") else []
params = {
"crawlerOptions": {
"includes": includes or [],
"excludes": excludes or [],
"generateImgAltText": True,
"limit": options.get("limit", 1),
"returnOnlyUrls": False,
"pageOptions": {"onlyMainContent": only_main_content, "includeHtml": False},
}
}
if options.get("max_depth"):
params["crawlerOptions"]["maxDepth"] = options.get("max_depth")
job_id = firecrawl_app.crawl_url(url, params)
website_crawl_time_cache_key = f"website_crawl_{job_id}"
time = str(datetime.datetime.now().timestamp())
redis_client.setex(website_crawl_time_cache_key, 3600, time)
return {"status": "active", "job_id": job_id}
elif provider == "jinareader":
api_key = encrypter.decrypt_token(
tenant_id=current_user.current_tenant_id, token=credentials.get("config").get("api_key")
)
crawl_sub_pages = options.get("crawl_sub_pages", False)
if not crawl_sub_pages:
response = requests.get(
f"https://r.jina.ai/{url}",
headers={"Accept": "application/json", "Authorization": f"Bearer {api_key}"},
)
if response.json().get("code") != 200:
raise ValueError("Failed to crawl")
return {"status": "active", "data": response.json().get("data")}
else:
response = requests.post(
"https://adaptivecrawl-kir3wx7b3a-uc.a.run.app",
json={
"url": url,
"maxPages": options.get("limit", 1),
"useSitemap": options.get("use_sitemap", True),
},
headers={
"Content-Type": "application/json",
"Authorization": f"Bearer {api_key}",
},
)
if response.json().get("code") != 200:
raise ValueError("Failed to crawl")
return {"status": "active", "job_id": response.json().get("data", {}).get("taskId")}
else:
raise ValueError("Invalid provider")
@classmethod
def get_crawl_status(cls, job_id: str, provider: str) -> dict:
credentials = ApiKeyAuthService.get_auth_credentials(current_user.current_tenant_id, "website", provider)
if provider == "firecrawl":
# decrypt api_key
api_key = encrypter.decrypt_token(
tenant_id=current_user.current_tenant_id, token=credentials.get("config").get("api_key")
)
firecrawl_app = FirecrawlApp(api_key=api_key, base_url=credentials.get("config").get("base_url", None))
result = firecrawl_app.check_crawl_status(job_id)
crawl_status_data = {
"status": result.get("status", "active"),
"job_id": job_id,
"total": result.get("total", 0),
"current": result.get("current", 0),
"data": result.get("data", []),
}
if crawl_status_data["status"] == "completed":
website_crawl_time_cache_key = f"website_crawl_{job_id}"
start_time = redis_client.get(website_crawl_time_cache_key)
if start_time:
end_time = datetime.datetime.now().timestamp()
time_consuming = abs(end_time - float(start_time))
crawl_status_data["time_consuming"] = f"{time_consuming:.2f}"
redis_client.delete(website_crawl_time_cache_key)
elif provider == "jinareader":
api_key = encrypter.decrypt_token(
tenant_id=current_user.current_tenant_id, token=credentials.get("config").get("api_key")
)
response = requests.post(
"https://adaptivecrawlstatus-kir3wx7b3a-uc.a.run.app",
headers={"Content-Type": "application/json", "Authorization": f"Bearer {api_key}"},
json={"taskId": job_id},
)
data = response.json().get("data", {})
crawl_status_data = {
"status": data.get("status", "active"),
"job_id": job_id,
"total": len(data.get("urls", [])),
"current": len(data.get("processed", [])) + len(data.get("failed", [])),
"data": [],
"time_consuming": data.get("duration", 0) / 1000,
}
if crawl_status_data["status"] == "completed":
response = requests.post(
"https://adaptivecrawlstatus-kir3wx7b3a-uc.a.run.app",
headers={"Content-Type": "application/json", "Authorization": f"Bearer {api_key}"},
json={"taskId": job_id, "urls": list(data.get("processed", {}).keys())},
)
data = response.json().get("data", {})
formatted_data = [
{
"title": item.get("data", {}).get("title"),
"source_url": item.get("data", {}).get("url"),
"description": item.get("data", {}).get("description"),
"markdown": item.get("data", {}).get("content"),
}
for item in data.get("processed", {}).values()
]
crawl_status_data["data"] = formatted_data
else:
raise ValueError("Invalid provider")
return crawl_status_data
@classmethod
def get_crawl_url_data(cls, job_id: str, provider: str, url: str, tenant_id: str) -> dict | None:
credentials = ApiKeyAuthService.get_auth_credentials(tenant_id, "website", provider)
# decrypt api_key
api_key = encrypter.decrypt_token(tenant_id=tenant_id, token=credentials.get("config").get("api_key"))
if provider == "firecrawl":
file_key = "website_files/" + job_id + ".txt"
if storage.exists(file_key):
data = storage.load_once(file_key)
if data:
data = json.loads(data.decode("utf-8"))
else:
firecrawl_app = FirecrawlApp(api_key=api_key, base_url=credentials.get("config").get("base_url", None))
result = firecrawl_app.check_crawl_status(job_id)
if result.get("status") != "completed":
raise ValueError("Crawl job is not completed")
data = result.get("data")
if data:
for item in data:
if item.get("source_url") == url:
return item
return None
elif provider == "jinareader":
file_key = "website_files/" + job_id + ".txt"
if storage.exists(file_key):
data = storage.load_once(file_key)
if data:
data = json.loads(data.decode("utf-8"))
elif not job_id:
response = requests.get(
f"https://r.jina.ai/{url}",
headers={"Accept": "application/json", "Authorization": f"Bearer {api_key}"},
)
if response.json().get("code") != 200:
raise ValueError("Failed to crawl")
return response.json().get("data")
else:
api_key = encrypter.decrypt_token(tenant_id=tenant_id, token=credentials.get("config").get("api_key"))
response = requests.post(
"https://adaptivecrawlstatus-kir3wx7b3a-uc.a.run.app",
headers={"Content-Type": "application/json", "Authorization": f"Bearer {api_key}"},
json={"taskId": job_id},
)
data = response.json().get("data", {})
if data.get("status") != "completed":
raise ValueError("Crawl job is not completed")
response = requests.post(
"https://adaptivecrawlstatus-kir3wx7b3a-uc.a.run.app",
headers={"Content-Type": "application/json", "Authorization": f"Bearer {api_key}"},
json={"taskId": job_id, "urls": list(data.get("processed", {}).keys())},
)
data = response.json().get("data", {})
for item in data.get("processed", {}).values():
if item.get("data", {}).get("url") == url:
return item.get("data", {})
else:
raise ValueError("Invalid provider")
@classmethod
def get_scrape_url_data(cls, provider: str, url: str, tenant_id: str, only_main_content: bool) -> dict | None:
credentials = ApiKeyAuthService.get_auth_credentials(tenant_id, "website", provider)
if provider == "firecrawl":
# decrypt api_key
api_key = encrypter.decrypt_token(tenant_id=tenant_id, token=credentials.get("config").get("api_key"))
firecrawl_app = FirecrawlApp(api_key=api_key, base_url=credentials.get("config").get("base_url", None))
params = {"pageOptions": {"onlyMainContent": only_main_content, "includeHtml": False}}
result = firecrawl_app.scrape_url(url, params)
return result
else:
raise ValueError("Invalid provider")
|