Floke/Brancheneinstufung2
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

[2ff88f42] Full End-to-End integration: Webhooks, Auto-Enrichment, Notion-Sync, UI updates and new Connector Architecture

Browse Source
This commit is contained in:
Floke
2026-02-19 16:05:52 +00:00
parent 0142f763f0
commit 138bb4acae
24 changed files with 1107 additions and 203 deletions
Download Patch File Download Diff File Expand all files Collapse all files

171
company-explorer/backend/app.py
View File

@@ -32,7 +32,7 @@ setup_logging()
import logging
logger = logging.getLogger(__name__)
from .database import init_db, get_db, Company, Signal, EnrichmentData, RoboticsCategory, Contact, Industry, JobRoleMapping, ReportedMistake
from .database import init_db, get_db, Company, Signal, EnrichmentData, RoboticsCategory, Contact, Industry, JobRoleMapping, ReportedMistake, MarketingMatrix
from .services.deduplication import Deduplicator
from .services.discovery import DiscoveryService
from .services.scraping import ScraperService
@@ -42,8 +42,7 @@ from .services.classification import ClassificationService
app = FastAPI(
title=settings.APP_NAME,
version=settings.VERSION,
description="Backend for Company Explorer (Robotics Edition)",
root_path="/ce"
description="Backend for Company Explorer (Robotics Edition)"
)
app.add_middleware(
@@ -65,6 +64,7 @@ class CompanyCreate(BaseModel):
city: Optional[str] = None
country: str = "DE"
website: Optional[str] = None
crm_id: Optional[str] = None
class BulkImportRequest(BaseModel):
names: List[str]
@@ -84,6 +84,20 @@ class ReportMistakeRequest(BaseModel):
quote: Optional[str] = None
user_comment: Optional[str] = None
class ProvisioningRequest(BaseModel):
so_contact_id: int
so_person_id: Optional[int] = None
crm_name: Optional[str] = None
crm_website: Optional[str] = None
class ProvisioningResponse(BaseModel):
status: str
company_name: str
website: Optional[str] = None
vertical_name: Optional[str] = None
role_name: Optional[str] = None
texts: Dict[str, Optional[str]] = {}
# --- Events ---
@app.on_event("startup")
def on_startup():
@@ -100,6 +114,141 @@ def on_startup():
def health_check(username: str = Depends(authenticate_user)):
return {"status": "ok", "version": settings.VERSION, "db": settings.DATABASE_URL}
@app.post("/api/provision/superoffice-contact", response_model=ProvisioningResponse)
def provision_superoffice_contact(
req: ProvisioningRequest,
background_tasks: BackgroundTasks,
db: Session = Depends(get_db),
username: str = Depends(authenticate_user)
):
# 1. Find Company (via SO ID)
company = db.query(Company).filter(Company.crm_id == str(req.so_contact_id)).first()
if not company:
# AUTO-CREATE Logic
if not req.crm_name:
# Cannot create without name. Should ideally not happen if Connector does its job.
raise HTTPException(400, "Cannot create company: crm_name missing")
company = Company(
name=req.crm_name,
crm_id=str(req.so_contact_id),
crm_name=req.crm_name,
crm_website=req.crm_website,
status="NEW"
)
db.add(company)
db.commit()
db.refresh(company)
logger.info(f"Auto-created company {company.name} from SuperOffice request.")
# Trigger Discovery
background_tasks.add_task(run_discovery_task, company.id)
return ProvisioningResponse(
status="processing",
company_name=company.name
)
# 1b. Check Status & Progress
# If NEW or DISCOVERED, we are not ready to provide texts.
if company.status in ["NEW", "DISCOVERED"]:
# If we have a website, ensure analysis is triggered
if company.status == "DISCOVERED" or (company.website and company.website != "k.A."):
background_tasks.add_task(run_analysis_task, company.id)
elif company.status == "NEW":
# Ensure discovery runs
background_tasks.add_task(run_discovery_task, company.id)
return ProvisioningResponse(
status="processing",
company_name=company.name
)
# 1c. Update CRM Snapshot Data (The Double Truth)
changed = False
if req.crm_name:
company.crm_name = req.crm_name
changed = True
if req.crm_website:
company.crm_website = req.crm_website
changed = True
# Simple Mismatch Check
if company.website and company.crm_website:
def norm(u): return str(u).lower().replace("https://", "").replace("http://", "").replace("www.", "").strip("/")
if norm(company.website) != norm(company.crm_website):
company.data_mismatch_score = 0.8 # High mismatch
changed = True
else:
if company.data_mismatch_score != 0.0:
company.data_mismatch_score = 0.0
changed = True
if changed:
company.updated_at = datetime.utcnow()
db.commit()
# 2. Find Contact (Person)
if req.so_person_id is None:
# Just a company sync, no texts needed
return ProvisioningResponse(
status="success",
company_name=company.name,
website=company.website,
vertical_name=company.industry_ai
)
person = db.query(Contact).filter(Contact.so_person_id == req.so_person_id).first()
# 3. Determine Role
role_name = None
if person and person.role:
role_name = person.role
elif req.job_title:
# Simple classification fallback
mappings = db.query(JobRoleMapping).all()
for m in mappings:
# Check pattern type (Regex vs Simple) - simplified here
pattern_clean = m.pattern.replace("%", "").lower()
if pattern_clean in req.job_title.lower():
role_name = m.role
break
# 4. Determine Vertical (Industry)
vertical_name = company.industry_ai
# 5. Fetch Texts from Matrix
texts = {"subject": None, "intro": None, "social_proof": None}
if vertical_name and role_name:
industry_obj = db.query(Industry).filter(Industry.name == vertical_name).first()
if industry_obj:
# Find any mapping for this role to query the Matrix
# (Assuming Matrix is linked to *one* canonical mapping for this role string)
role_ids = [m.id for m in db.query(JobRoleMapping).filter(JobRoleMapping.role == role_name).all()]
if role_ids:
matrix_entry = db.query(MarketingMatrix).filter(
MarketingMatrix.industry_id == industry_obj.id,
MarketingMatrix.role_id.in_(role_ids)
).first()
if matrix_entry:
texts["subject"] = matrix_entry.subject
texts["intro"] = matrix_entry.intro
texts["social_proof"] = matrix_entry.social_proof
return ProvisioningResponse(
status="success",
company_name=company.name,
website=company.website,
vertical_name=vertical_name,
role_name=role_name,
texts=texts
)
@app.get("/api/companies")
def list_companies(
skip: int = 0,
@@ -234,6 +383,7 @@ def create_company(company: CompanyCreate, db: Session = Depends(get_db), userna
city=company.city,
country=company.country,
website=company.website,
crm_id=company.crm_id,
status="NEW"
)
db.add(new_company)
@@ -665,10 +815,23 @@ def run_analysis_task(company_id: int):
# --- Serve Frontend ---
static_path = "/frontend_static"
if not os.path.exists(static_path):
static_path = os.path.join(os.path.dirname(__file__), "../static")
# Local dev fallback
static_path = os.path.join(os.path.dirname(__file__), "../../frontend/dist")
if not os.path.exists(static_path):
static_path = os.path.join(os.path.dirname(__file__), "../static")
logger.info(f"Static files path: {static_path} (Exists: {os.path.exists(static_path)})")
if os.path.exists(static_path):
@app.get("/")
async def serve_index():
return FileResponse(os.path.join(static_path, "index.html"))
app.mount("/", StaticFiles(directory=static_path, html=True), name="static")
else:
@app.get("/")
def root_no_frontend():
return {"message": "Company Explorer API is running, but frontend was not found.", "path_tried": static_path}
if __name__ == "__main__":
import uvicorn

28
company-explorer/backend/database.py
View File

@@ -93,6 +93,10 @@ class Contact(Base):
job_title = Column(String) # Visitenkarten-Titel
language = Column(String, default="De") # "De", "En"
# SuperOffice Mapping
so_contact_id = Column(Integer, nullable=True, index=True) # SuperOffice Contact ID (Company)
so_person_id = Column(Integer, nullable=True, unique=True, index=True) # SuperOffice Person ID
role = Column(String) # Operativer Entscheider, etc.
status = Column(String, default="") # Marketing Status
@@ -248,6 +252,30 @@ class ReportedMistake(Base):
company = relationship("Company", back_populates="reported_mistakes")
class MarketingMatrix(Base):
"""
Stores the static marketing texts for Industry x Role combinations.
Source: Notion (synced).
"""
__tablename__ = "marketing_matrix"
id = Column(Integer, primary_key=True, index=True)
# The combination keys
industry_id = Column(Integer, ForeignKey("industries.id"), nullable=False)
role_id = Column(Integer, ForeignKey("job_role_mappings.id"), nullable=False)
# The Content
subject = Column(Text, nullable=True)
intro = Column(Text, nullable=True)
social_proof = Column(Text, nullable=True)
updated_at = Column(DateTime, default=datetime.utcnow, onupdate=datetime.utcnow)
industry = relationship("Industry")
role = relationship("JobRoleMapping")
# ==============================================================================
# UTILS
# ==============================================================================

14
company-explorer/backend/scripts/sync_notion_to_ce_enhanced.py
View File

@@ -72,6 +72,10 @@ def extract_select(prop):
if not prop or "select" not in prop or not prop["select"]: return ""
return prop["select"]["name"]
def extract_number(prop):
if not prop or "number" not in prop: return None
return prop["number"]
def sync():
logger.info("--- Starting Enhanced Sync ---")
@@ -131,6 +135,16 @@ def sync():
ind.pains = extract_rich_text(props.get("Pains"))
ind.gains = extract_rich_text(props.get("Gains"))
# Metrics & Scraper Config (NEW)
ind.metric_type = extract_select(props.get("Metric Type"))
ind.min_requirement = extract_number(props.get("Min. Requirement"))
ind.whale_threshold = extract_number(props.get("Whale Threshold"))
ind.proxy_factor = extract_number(props.get("Proxy Factor"))
ind.scraper_search_term = extract_rich_text(props.get("Scraper Search Term"))
ind.scraper_keywords = extract_rich_text(props.get("Scraper Keywords"))
ind.standardization_logic = extract_rich_text(props.get("Standardization Logic"))
# Status / Priority
prio = extract_select(props.get("Priorität"))
if not prio: prio = extract_select(props.get("Freigegeben"))