forked from 0xWheatyz/SPARC
Compare commits
1 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
| 0b4d712fc5 |
+13
-1
@@ -1,3 +1,4 @@
|
|||||||
|
import logging
|
||||||
import os
|
import os
|
||||||
import re
|
import re
|
||||||
from datetime import datetime, timedelta
|
from datetime import datetime, timedelta
|
||||||
@@ -10,6 +11,8 @@ 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:
|
||||||
@@ -44,6 +47,7 @@ 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 = []
|
||||||
@@ -52,8 +56,10 @@ 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))
|
||||||
# Patents without PDF links are skipped (see docstring for details)
|
else:
|
||||||
|
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:
|
||||||
@@ -70,9 +76,13 @@ 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
|
||||||
@@ -90,11 +100,13 @@ 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 = {
|
||||||
|
|||||||
@@ -9,38 +9,15 @@ const COLORS = ['#6366f1', '#0ea5e9', '#10b981', '#f59e0b', '#ef4444', '#8b5cf6'
|
|||||||
export function AnalyticsPage() {
|
export function AnalyticsPage() {
|
||||||
const [days, setDays] = useState(30);
|
const [days, setDays] = useState(30);
|
||||||
|
|
||||||
const { data, isLoading, isError, refetch } = useQuery({
|
const { data, isLoading, isError } = useQuery({
|
||||||
queryKey: ['analytics', days],
|
queryKey: ['analytics', days],
|
||||||
queryFn: () => analyticsApi.getAnalytics(days),
|
queryFn: () => analyticsApi.getAnalytics(days),
|
||||||
});
|
});
|
||||||
|
|
||||||
if (isLoading) {
|
if (isLoading) {
|
||||||
return (
|
return (
|
||||||
<div className="space-y-6">
|
<div className="flex items-center justify-center min-h-[400px]">
|
||||||
<div>
|
<div className="animate-spin rounded-full h-12 w-12 border-t-2 border-b-2 border-primary"></div>
|
||||||
<h2 className="text-xl font-semibold text-text-primary border-b-2 border-primary/30 pb-2 mb-2">
|
|
||||||
Analytics Dashboard
|
|
||||||
</h2>
|
|
||||||
<p className="text-text-secondary">Loading analytics data...</p>
|
|
||||||
</div>
|
|
||||||
{/* Skeleton cards */}
|
|
||||||
<div className="grid grid-cols-1 md:grid-cols-3 gap-4">
|
|
||||||
{[1, 2, 3].map((i) => (
|
|
||||||
<div key={i} className="bg-gradient-to-br from-primary/10 to-secondary/10 border border-primary/20 rounded-xl p-5 text-center animate-pulse">
|
|
||||||
<div className="h-9 w-16 bg-primary/20 rounded mx-auto mb-2" />
|
|
||||||
<div className="h-4 w-24 bg-primary/10 rounded mx-auto" />
|
|
||||||
</div>
|
|
||||||
))}
|
|
||||||
</div>
|
|
||||||
{/* Skeleton charts */}
|
|
||||||
<div className="grid grid-cols-1 lg:grid-cols-2 gap-6">
|
|
||||||
{[1, 2].map((i) => (
|
|
||||||
<div key={i} className="bg-bg-card/60 border border-primary/15 rounded-2xl p-6 animate-pulse">
|
|
||||||
<div className="h-5 w-40 bg-primary/20 rounded mb-4" />
|
|
||||||
<div className="h-[300px] bg-primary/5 rounded" />
|
|
||||||
</div>
|
|
||||||
))}
|
|
||||||
</div>
|
|
||||||
</div>
|
</div>
|
||||||
);
|
);
|
||||||
}
|
}
|
||||||
@@ -56,18 +33,15 @@ export function AnalyticsPage() {
|
|||||||
<div className="bg-gradient-to-br from-primary/10 to-secondary/5 border border-primary/20 rounded-xl p-6">
|
<div className="bg-gradient-to-br from-primary/10 to-secondary/5 border border-primary/20 rounded-xl p-6">
|
||||||
<div className="flex items-center gap-3 text-warning mb-2">
|
<div className="flex items-center gap-3 text-warning mb-2">
|
||||||
<Database size={24} />
|
<Database size={24} />
|
||||||
<span className="font-semibold">Unable to Load Analytics</span>
|
<span className="font-semibold">Database Not Connected</span>
|
||||||
</div>
|
</div>
|
||||||
<p className="text-text-secondary">
|
<p className="text-text-secondary">
|
||||||
Could not connect to the analytics database. Ensure PostgreSQL is running and
|
Set <code className="bg-bg-card px-2 py-1 rounded">USE_DATABASE=true</code> in your .env file to enable analytics tracking.
|
||||||
<code className="bg-bg-card px-2 py-1 rounded mx-1">DATABASE_URL</code> is configured correctly.
|
|
||||||
</p>
|
</p>
|
||||||
<button
|
</div>
|
||||||
onClick={() => refetch()}
|
<div className="flex items-center gap-2 bg-secondary/10 border border-secondary/20 text-secondary rounded-xl px-4 py-3">
|
||||||
className="mt-3 text-sm bg-primary/20 hover:bg-primary/30 text-primary font-medium px-4 py-2 rounded-lg transition-colors"
|
<AlertCircle size={18} />
|
||||||
>
|
<span>Analytics features require storing analysis results in PostgreSQL for historical tracking.</span>
|
||||||
Retry
|
|
||||||
</button>
|
|
||||||
</div>
|
</div>
|
||||||
</div>
|
</div>
|
||||||
);
|
);
|
||||||
|
|||||||
@@ -114,21 +114,9 @@ export function Batch() {
|
|||||||
|
|
||||||
{/* Error */}
|
{/* Error */}
|
||||||
{mutation.isError && (
|
{mutation.isError && (
|
||||||
<div className="bg-error/10 border border-error/20 rounded-xl px-4 py-3">
|
<div className="flex items-center gap-2 bg-error/10 border border-error/20 text-error rounded-xl px-4 py-3">
|
||||||
<div className="flex items-center gap-2 text-error">
|
<AlertCircle size={18} />
|
||||||
<AlertCircle size={18} />
|
<span>Batch analysis failed. Please try again.</span>
|
||||||
<span className="font-semibold">Batch analysis failed</span>
|
|
||||||
</div>
|
|
||||||
<p className="text-text-secondary text-sm mt-1 ml-7">
|
|
||||||
{mutation.error instanceof Error ? mutation.error.message : 'An unexpected error occurred.'}
|
|
||||||
{' '}Check your connection and try again.
|
|
||||||
</p>
|
|
||||||
<button
|
|
||||||
onClick={() => mutation.reset()}
|
|
||||||
className="ml-7 mt-2 text-sm text-primary hover:text-primary-dark underline"
|
|
||||||
>
|
|
||||||
Dismiss
|
|
||||||
</button>
|
|
||||||
</div>
|
</div>
|
||||||
)}
|
)}
|
||||||
|
|
||||||
|
|||||||
Reference in New Issue
Block a user