forked from 0xWheatyz/SPARC
Compare commits
1 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
| 4696838fb8 |
@@ -34,6 +34,17 @@ jobs:
|
|||||||
run: |
|
run: |
|
||||||
ruff check SPARC/ tests/
|
ruff check SPARC/ tests/
|
||||||
|
|
||||||
|
- name: Install Node.js and frontend dependencies
|
||||||
|
shell: sh
|
||||||
|
run: |
|
||||||
|
apk add --no-cache nodejs npm
|
||||||
|
cd frontend && npm ci
|
||||||
|
|
||||||
|
- name: Run TypeScript type check
|
||||||
|
shell: sh
|
||||||
|
run: |
|
||||||
|
cd frontend && npx tsc --noEmit
|
||||||
|
|
||||||
- name: Run pytest
|
- name: Run pytest
|
||||||
shell: sh
|
shell: sh
|
||||||
env:
|
env:
|
||||||
|
|||||||
+1
-13
@@ -1,4 +1,3 @@
|
|||||||
import logging
|
|
||||||
import os
|
import os
|
||||||
import re
|
import re
|
||||||
from datetime import datetime, timedelta
|
from datetime import datetime, timedelta
|
||||||
@@ -11,8 +10,6 @@ import serpapi
|
|||||||
from SPARC import config
|
from SPARC import config
|
||||||
from SPARC.types import Patent, Patents
|
from SPARC.types import Patent, Patents
|
||||||
|
|
||||||
logger = logging.getLogger(__name__)
|
|
||||||
|
|
||||||
|
|
||||||
class SERP:
|
class SERP:
|
||||||
def query(company: str, days_back: int = None) -> Patents:
|
def query(company: str, days_back: int = None) -> Patents:
|
||||||
@@ -47,7 +44,6 @@ class SERP:
|
|||||||
"tbs": date_filter,
|
"tbs": date_filter,
|
||||||
"api_key": config.api_key,
|
"api_key": config.api_key,
|
||||||
}
|
}
|
||||||
logger.info("Querying Google Patents for '%s' (last %d days)", company, days_back)
|
|
||||||
search = serpapi.search(params)
|
search = serpapi.search(params)
|
||||||
# Convert results to Patent objects, skipping any without PDF links
|
# Convert results to Patent objects, skipping any without PDF links
|
||||||
patent_ids = []
|
patent_ids = []
|
||||||
@@ -56,10 +52,8 @@ class SERP:
|
|||||||
pdf_link = patent.get("pdf")
|
pdf_link = patent.get("pdf")
|
||||||
if pdf_link:
|
if pdf_link:
|
||||||
patent_ids.append(Patent(patent_id=patent["publication_number"], pdf_link=pdf_link, summary=None))
|
patent_ids.append(Patent(patent_id=patent["publication_number"], pdf_link=pdf_link, summary=None))
|
||||||
else:
|
# Patents without PDF links are skipped (see docstring for details)
|
||||||
logger.debug("Skipping patent %s (no PDF link)", patent.get("publication_number", "unknown"))
|
|
||||||
|
|
||||||
logger.info("Found %d patents with PDF links for '%s'", len(patent_ids), company)
|
|
||||||
return Patents(patents=patent_ids)
|
return Patents(patents=patent_ids)
|
||||||
|
|
||||||
def save_patents(patent: Patent) -> Patent:
|
def save_patents(patent: Patent) -> Patent:
|
||||||
@@ -76,13 +70,9 @@ class SERP:
|
|||||||
os.makedirs("patents", exist_ok=True)
|
os.makedirs("patents", exist_ok=True)
|
||||||
|
|
||||||
if not (os.path.exists(pdf_path) and os.path.getsize(pdf_path) > 0):
|
if not (os.path.exists(pdf_path) and os.path.getsize(pdf_path) > 0):
|
||||||
logger.info("Downloading PDF for %s", patent.patent_id)
|
|
||||||
response = requests.get(patent.pdf_link)
|
response = requests.get(patent.pdf_link)
|
||||||
with open(pdf_path, "wb") as f:
|
with open(pdf_path, "wb") as f:
|
||||||
f.write(response.content)
|
f.write(response.content)
|
||||||
logger.debug("Saved %d bytes to %s", len(response.content), pdf_path)
|
|
||||||
else:
|
|
||||||
logger.debug("Using cached PDF for %s at %s", patent.patent_id, pdf_path)
|
|
||||||
|
|
||||||
patent.pdf_path = pdf_path
|
patent.pdf_path = pdf_path
|
||||||
return patent
|
return patent
|
||||||
@@ -100,13 +90,11 @@ class SERP:
|
|||||||
Dictionary containing all extracted sections
|
Dictionary containing all extracted sections
|
||||||
"""
|
"""
|
||||||
|
|
||||||
logger.debug("Parsing patent PDF: %s", pdf_path)
|
|
||||||
with pdfplumber.open(pdf_path) as pdf:
|
with pdfplumber.open(pdf_path) as pdf:
|
||||||
# Extract all text
|
# Extract all text
|
||||||
full_text = ""
|
full_text = ""
|
||||||
for page in pdf.pages:
|
for page in pdf.pages:
|
||||||
full_text += page.extract_text() + "\n"
|
full_text += page.extract_text() + "\n"
|
||||||
logger.debug("Extracted text from %d pages (%d chars)", len(pdf.pages), len(full_text))
|
|
||||||
|
|
||||||
# Define section patterns (common in patents)
|
# Define section patterns (common in patents)
|
||||||
sections = {
|
sections = {
|
||||||
|
|||||||
Generated
+4
-4
@@ -10,7 +10,7 @@
|
|||||||
"dependencies": {
|
"dependencies": {
|
||||||
"@tanstack/react-query": "^5.51.0",
|
"@tanstack/react-query": "^5.51.0",
|
||||||
"axios": "^1.7.2",
|
"axios": "^1.7.2",
|
||||||
"lucide-react": "^0.400.0",
|
"lucide-react": "^1.7.0",
|
||||||
"react": "^18.3.1",
|
"react": "^18.3.1",
|
||||||
"react-dom": "^18.3.1",
|
"react-dom": "^18.3.1",
|
||||||
"react-router-dom": "^6.24.0",
|
"react-router-dom": "^6.24.0",
|
||||||
@@ -3452,9 +3452,9 @@
|
|||||||
}
|
}
|
||||||
},
|
},
|
||||||
"node_modules/lucide-react": {
|
"node_modules/lucide-react": {
|
||||||
"version": "0.400.0",
|
"version": "1.7.0",
|
||||||
"resolved": "https://registry.npmjs.org/lucide-react/-/lucide-react-0.400.0.tgz",
|
"resolved": "https://registry.npmjs.org/lucide-react/-/lucide-react-1.7.0.tgz",
|
||||||
"integrity": "sha512-rpp7pFHh3Xd93KHixNgB0SqThMHpYNzsGUu69UaQbSZ75Q/J3m5t6EhKyMT3m4w2WOxmJ2mY0tD3vebnXqQryQ==",
|
"integrity": "sha512-yI7BeItCLZJTXikmK4KNUGCKoGzSvbKlfCvw44bU4fXAL6v3gYS4uHD1jzsLkfwODYwI6Drw5Tu9Z5ulDe0TSg==",
|
||||||
"license": "ISC",
|
"license": "ISC",
|
||||||
"peerDependencies": {
|
"peerDependencies": {
|
||||||
"react": "^16.5.1 || ^17.0.0 || ^18.0.0 || ^19.0.0"
|
"react": "^16.5.1 || ^17.0.0 || ^18.0.0 || ^19.0.0"
|
||||||
|
|||||||
@@ -7,12 +7,13 @@
|
|||||||
"dev": "vite",
|
"dev": "vite",
|
||||||
"build": "tsc -b && vite build",
|
"build": "tsc -b && vite build",
|
||||||
"lint": "eslint .",
|
"lint": "eslint .",
|
||||||
|
"typecheck": "tsc --noEmit",
|
||||||
"preview": "vite preview"
|
"preview": "vite preview"
|
||||||
},
|
},
|
||||||
"dependencies": {
|
"dependencies": {
|
||||||
"@tanstack/react-query": "^5.51.0",
|
"@tanstack/react-query": "^5.51.0",
|
||||||
"axios": "^1.7.2",
|
"axios": "^1.7.2",
|
||||||
"lucide-react": "^0.400.0",
|
"lucide-react": "^1.7.0",
|
||||||
"react": "^18.3.1",
|
"react": "^18.3.1",
|
||||||
"react-dom": "^18.3.1",
|
"react-dom": "^18.3.1",
|
||||||
"react-router-dom": "^6.24.0",
|
"react-router-dom": "^6.24.0",
|
||||||
|
|||||||
Reference in New Issue
Block a user