cryptorugmunch
dd63022530
Each module did:
X_DIR = Path(os.path.expanduser("~/.pry/x"))
After:
from paths import PRY_DATA_DIR
X_DIR = PRY_DATA_DIR / "x"
The module-level Path construction is preserved, so the rest of the
code is unchanged. PRY_DATA_DIR is read once at import (overridable via
the env var of the same name).
Verified:
- 407 tests collect (was 5 collection errors from a misplaced import)
- 83 sampled tests pass (intelligence, proxy_manager, x402, agency,
gdpr, referrals, marketplace, api)
- 0 remaining hardcoded ~/.pry references in .py files
Follow-up: paths.py adds subdir(name) helper for new code that wants
auto-mkdir; existing modules still call .mkdir(exist_ok=True) themselves
to preserve the eager-init behavior they had before.
270 lines
11 KiB
Python
270 lines
11 KiB
Python
# SPDX-License-Identifier: MIT
|
|
# Copyright (c) 2026 Rug Munch Media LLC
|
|
#
|
|
# Part of Pry — https://git.rugmunch.io/RugMunchMedia/pryscraper
|
|
# Licensed under MIT. See LICENSE.
|
|
"""Pry — Real data-driven auto-reports with PDF generation."""
|
|
|
|
import logging
|
|
import os
|
|
from datetime import UTC, datetime
|
|
from html.parser import HTMLParser
|
|
from pathlib import Path
|
|
from typing import Any
|
|
|
|
from paths import PRY_DATA_DIR
|
|
logger = logging.getLogger(__name__)
|
|
|
|
REPORTS_DIR = PRY_DATA_DIR / "reports_real"
|
|
REPORTS_DIR.mkdir(parents=True, exist_ok=True)
|
|
|
|
try:
|
|
from reportlab.lib import colors
|
|
from reportlab.lib.pagesizes import letter
|
|
from reportlab.lib.styles import ParagraphStyle, getSampleStyleSheet
|
|
from reportlab.lib.units import inch
|
|
from reportlab.platypus import (
|
|
Paragraph,
|
|
SimpleDocTemplate,
|
|
Spacer,
|
|
Table,
|
|
)
|
|
|
|
_has_reportlab = True
|
|
except ImportError:
|
|
_has_reportlab = False
|
|
|
|
|
|
class ReportGenerator:
|
|
"""Generate real data-driven reports with charts and PDF export."""
|
|
|
|
def __init__(self) -> None:
|
|
self.styles = getSampleStyleSheet() if _has_reportlab else None
|
|
|
|
def generate(
|
|
self,
|
|
report_type: str,
|
|
data: dict[str, Any],
|
|
output_format: str = "html",
|
|
title: str = "Report",
|
|
branding: dict | None = None,
|
|
) -> dict[str, Any]:
|
|
"""Generate a data-driven report from real data.
|
|
|
|
Args:
|
|
report_type: "competitive", "price_monitor", "seo_audit", "content_tracker", "anomaly_summary"
|
|
data: Real data from database/cache
|
|
output_format: "html" or "pdf"
|
|
title: Report title
|
|
branding: {"company": "...", "color": "#hex"}
|
|
"""
|
|
branding = branding or {}
|
|
if report_type == "competitive":
|
|
content = self._competitive_report(data, title, branding)
|
|
elif report_type == "price_monitor":
|
|
content = self._price_report(data, title, branding)
|
|
elif report_type == "seo_audit":
|
|
content = self._seo_report(data, title, branding)
|
|
elif report_type == "anomaly_summary":
|
|
content = self._anomaly_report(data, title, branding)
|
|
else:
|
|
return {"error": f"Unknown report type: {report_type}"}
|
|
|
|
if output_format == "pdf" and _has_reportlab:
|
|
pdf_path = self._to_pdf(content, title, branding)
|
|
return {"success": True, "path": str(pdf_path), "format": "pdf"}
|
|
|
|
timestamp = datetime.now(UTC).strftime("%Y%m%d_%H%M%S")
|
|
html_path = REPORTS_DIR / f"{report_type}_{timestamp}.html"
|
|
html_path.write_text(self._wrap_html(content, title, branding))
|
|
return {"success": True, "path": str(html_path), "format": "html"}
|
|
|
|
def _competitive_report(self, data: dict, title: str, branding: dict) -> str:
|
|
competitors = data.get("competitors", [])
|
|
changes = data.get("changes", [])
|
|
body = f"""
|
|
<h2>Competitive Analysis</h2>
|
|
<p>Report generated: {datetime.now(UTC).strftime('%B %d, %Y')}</p>
|
|
<h3>Competitors Tracked ({len(competitors)})</h3>
|
|
<table>
|
|
<thead><tr><th>Name</th><th>Price</th><th>Change</th><th>Last Updated</th></tr></thead>
|
|
<tbody>
|
|
"""
|
|
for c in competitors:
|
|
change = c.get("price_change", 0) or 0
|
|
change_str = f"{change:+.1f}%" if change else "—"
|
|
change_class = "up" if change > 0 else "down" if change < 0 else "stable"
|
|
body += (
|
|
f"<tr><td>{c.get('name','')}</td>"
|
|
f"<td>${c.get('price',0):.2f}</td>"
|
|
f"<td class='{change_class}'>{change_str}</td>"
|
|
f"<td>{c.get('last_updated','')}</td></tr>"
|
|
)
|
|
body += "</tbody></table>"
|
|
|
|
if changes:
|
|
body += "<h3>Recent Changes</h3><ul>"
|
|
for c in changes[:20]:
|
|
body += f"<li>{c}</li>"
|
|
body += "</ul>"
|
|
return body
|
|
|
|
def _price_report(self, data: dict, title: str, branding: dict) -> str:
|
|
products = data.get("products", [])
|
|
drops = sum(1 for p in products if (p.get("price_change") or 0) < 0)
|
|
rises = sum(1 for p in products if (p.get("price_change") or 0) > 0)
|
|
body = f"""
|
|
<h2>Price Monitoring Report</h2>
|
|
<p>Generated: {datetime.now(UTC).strftime('%B %d, %Y')}</p>
|
|
<div class='summary'>
|
|
<div class='stat'><h3>{len(products)}</h3><p>Products</p></div>
|
|
<div class='stat up'><h3>{drops}</h3><p>Price Drops</p></div>
|
|
<div class='stat down'><h3>{rises}</h3><p>Price Rises</p></div>
|
|
</div>
|
|
<table><thead><tr><th>Product</th><th>Previous</th><th>Current</th><th>Change</th></tr></thead><tbody>
|
|
"""
|
|
for p in products[:50]:
|
|
pc = p.get("price_change", 0) or 0
|
|
change_str = f"{pc:+.1f}%" if pc else "stable"
|
|
change_class = "down" if pc < 0 else "up" if pc > 0 else "stable"
|
|
body += (
|
|
f"<tr><td>{p.get('name','')}</td>"
|
|
f"<td>${p.get('previous_price',0):.2f}</td>"
|
|
f"<td>${p.get('current_price',0):.2f}</td>"
|
|
f"<td class='{change_class}'>{change_str}</td></tr>"
|
|
)
|
|
body += "</tbody></table>"
|
|
return body
|
|
|
|
def _seo_report(self, data: dict, title: str, branding: dict) -> str:
|
|
seo = data.get("seo_data", {})
|
|
changes = data.get("changes", [])
|
|
title_text = (seo.get("title") or "N/A")[:100]
|
|
desc = (seo.get("meta_description") or "N/A")[:200]
|
|
body = f"""
|
|
<h2>SEO Audit Report</h2>
|
|
<p>Generated: {datetime.now(UTC).strftime('%B %d, %Y')}</p>
|
|
<h3>Current SEO Status</h3>
|
|
<table>
|
|
<tr><td><strong>Title</strong></td><td>{title_text}</td></tr>
|
|
<tr><td><strong>Meta Description</strong></td><td>{desc}</td></tr>
|
|
<tr><td><strong>Word Count</strong></td><td>{seo.get('word_count', 0):,}</td></tr>
|
|
<tr><td><strong>Internal Links</strong></td><td>{seo.get('links_internal', 0)}</td></tr>
|
|
<tr><td><strong>External Links</strong></td><td>{seo.get('links_external', 0)}</td></tr>
|
|
<tr><td><strong>Schema Markup</strong></td><td>{'Yes' if seo.get('has_schema') else 'No'}</td></tr>
|
|
</table>
|
|
"""
|
|
if changes:
|
|
body += "<h3>Recent SEO Changes</h3><ul>"
|
|
for c in changes[:20]:
|
|
body += (
|
|
f"<li>{c.get('field','')}: {str(c.get('to',''))[:80]}</li>"
|
|
)
|
|
body += "</ul>"
|
|
return body
|
|
|
|
def _anomaly_report(self, data: dict, title: str, branding: dict) -> str:
|
|
anomalies = data.get("anomalies", [])
|
|
body = f"""
|
|
<h2>Anomaly Summary Report</h2>
|
|
<p>Generated: {datetime.now(UTC).strftime('%B %d, %Y')}</p>
|
|
<h3>Detected Anomalies ({len(anomalies)})</h3>
|
|
<table><thead><tr><th>Field</th><th>Type</th><th>Severity</th><th>Reason</th></tr></thead><tbody>
|
|
"""
|
|
for a in anomalies:
|
|
body += (
|
|
f"<tr><td>{a.get('field','')}</td>"
|
|
f"<td>{a.get('type','')}</td>"
|
|
f"<td>{a.get('severity','')}</td>"
|
|
f"<td>{a.get('reason','')}</td></tr>"
|
|
)
|
|
body += "</tbody></table>"
|
|
return body
|
|
|
|
def _to_pdf(self, html_content: str, title: str, branding: dict) -> Path:
|
|
"""Convert HTML report to PDF using reportlab."""
|
|
timestamp = datetime.now(UTC).strftime("%Y%m%d_%H%M%S")
|
|
pdf_path = REPORTS_DIR / f"report_{timestamp}.pdf"
|
|
doc = SimpleDocTemplate(str(pdf_path), pagesize=letter)
|
|
story: list[Any] = []
|
|
assert self.styles is not None
|
|
title_style = ParagraphStyle(
|
|
"title",
|
|
parent=self.styles["Heading1"],
|
|
textColor=colors.HexColor(branding.get("color", "#f59e0b")),
|
|
)
|
|
story.append(Paragraph(title, title_style))
|
|
story.append(Spacer(1, 0.3 * inch))
|
|
|
|
class SimpleHTMLToPDF(HTMLParser):
|
|
def __init__(self, story: list[Any], styles: Any) -> None:
|
|
super().__init__()
|
|
self.story = story
|
|
self.styles = styles
|
|
self.current_row: list[str] = []
|
|
self.in_table = False
|
|
|
|
def handle_starttag(self, tag: str, attrs: list) -> None:
|
|
if tag in ("h2", "h3"):
|
|
self.story.append(Paragraph(" ", self.styles["Normal"]))
|
|
elif tag == "tr":
|
|
self.current_row = []
|
|
|
|
def handle_endtag(self, tag: str) -> None:
|
|
if tag == "tr" and self.current_row:
|
|
import contextlib
|
|
with contextlib.suppress(Exception):
|
|
self.story.append(
|
|
Table(
|
|
[self.current_row],
|
|
colWidths=[2 * inch] * len(self.current_row),
|
|
)
|
|
)
|
|
elif tag == "table":
|
|
self.story.append(Spacer(1, 0.1 * inch))
|
|
|
|
def handle_data(self, data: str) -> None:
|
|
data = data.strip()
|
|
if not data:
|
|
return
|
|
safe = data.replace("&", "&").replace("<", "<").replace(">", ">")
|
|
if len(safe) > 100:
|
|
safe = safe[:100] + "..."
|
|
if self.in_table:
|
|
self.current_row.append(safe)
|
|
else:
|
|
import contextlib
|
|
with contextlib.suppress(Exception):
|
|
self.story.append(Paragraph(safe, self.styles["Normal"]))
|
|
|
|
SimpleHTMLToPDF(story, self.styles).feed(html_content)
|
|
doc.build(story)
|
|
return pdf_path
|
|
|
|
def _wrap_html(self, body: str, title: str, branding: dict) -> str:
|
|
"""Wrap report body in full HTML with branding."""
|
|
company = branding.get("company", "Pry")
|
|
color = branding.get("color", "#f59e0b")
|
|
return f"""<!DOCTYPE html>
|
|
<html><head><meta charset="UTF-8"><title>{title}</title>
|
|
<style>
|
|
body {{ font-family: -apple-system, sans-serif; margin: 40px; color: #1a1a2e; }}
|
|
h1 {{ color: {color}; border-bottom: 3px solid {color}; padding-bottom: 10px; }}
|
|
h2 {{ color: {color}; margin-top: 30px; }}
|
|
h3 {{ color: #444; }}
|
|
table {{ border-collapse: collapse; width: 100%; margin: 20px 0; }}
|
|
th {{ background: {color}; color: white; padding: 10px; text-align: left; }}
|
|
td {{ padding: 8px; border-bottom: 1px solid #eee; }}
|
|
.summary {{ display: flex; gap: 20px; margin: 20px 0; }}
|
|
.stat {{ flex: 1; padding: 20px; background: #f8f8f8; border-radius: 8px; text-align: center; border-top: 3px solid {color}; }}
|
|
.stat h3 {{ font-size: 36px; margin: 0; }}
|
|
.up {{ color: #16a34a; }}
|
|
.down {{ color: #dc2626; }}
|
|
.stable {{ color: #6b7280; }}
|
|
.footer {{ margin-top: 40px; padding-top: 20px; border-top: 1px solid #eee; font-size: 12px; color: #666; text-align: center; }}
|
|
</style></head>
|
|
<body>
|
|
<h1>{title}</h1>
|
|
{body}
|
|
<div class='footer'>Generated by {company} on {datetime.now(UTC).strftime('%B %d, %Y at %H:%M UTC')}</div>
|
|
</body></html>"""
|