From 8a388ada5c0fd7eeb8f4df88548d96b469830b34 Mon Sep 17 00:00:00 2001
From: Fernando Ruiz Diaz <88462636+ferdlestier@users.noreply.github.com>
Date: Tue, 23 Jul 2024 15:23:33 -0400
Subject: [PATCH] Add PDF report generation for dataframes

---
 parser.py            | 31 +++++++++++++++++++++++++++++++
 requirements.txt     |  2 ++
 tests/test_parser.py | 28 +++++++++++++++++++++++++++-
 3 files changed, 60 insertions(+), 1 deletion(-)

diff --git a/parser.py b/parser.py
index e9b2344..968e067 100644
--- a/parser.py
+++ b/parser.py
@@ -3,6 +3,8 @@
 
 import pandas as pd
 import logging  # Import logging module
+import matplotlib.pyplot as plt
+from fpdf import FPDF
 
 # Configure logging
 logging.basicConfig(filename='parser.log', level=logging.DEBUG, format='%(asctime)s:%(levelname)s:%(message)s')
@@ -132,6 +134,35 @@
         logging.info(f"Fundamental data compared across industry group: {grupo}")
         logging.info(f"Number of records processed for industry group {grupo}: {len(industria)}")
 
+    # Generate PDF report
+    pdf = FPDF()
+    pdf.add_page()
+    pdf.set_font("Arial", size=12)
+
+    def add_dataframe_to_pdf(pdf, df, title):
+        pdf.set_font("Arial", 'B', 14)
+        pdf.cell(200, 10, txt=title, ln=True, align='C')
+        pdf.set_font("Arial", size=10)
+        pdf.ln(10)
+        for i in range(len(df)):
+            row = df.iloc[i]
+            for item in row:
+                pdf.cell(40, 10, txt=str(item), border=1)
+            pdf.ln(10)
+        pdf.ln(10)
+
+    add_dataframe_to_pdf(pdf, dailymovers.head(20), "Top 20 Daily Movers")
+    add_dataframe_to_pdf(pdf, dailymovers.tail(20), "Top 20 Daily Losers")
+    add_dataframe_to_pdf(pdf, pricetracker, "Top 20 Medium Term Price Change (Growth)")
+    add_dataframe_to_pdf(pdf, pricetrackerloss, "Top 20 Medium Term Price Change (Loss)")
+    add_dataframe_to_pdf(pdf, p_e, "Growth Potential Based on Analyst Recommendations")
+    add_dataframe_to_pdf(pdf, exposure.head(20), "Top 20 Financial Exposure")
+    add_dataframe_to_pdf(pdf, cap_return.head(20), "Top 20 Return on Invested Capital")
+    add_dataframe_to_pdf(pdf, fund_data.head(20), "Top 20 Fundamental Data")
+
+    pdf.output("report.pdf")
+    logging.info("PDF report generated successfully")
+
     logging.info("Script completed successfully")
 
 except Exception as e:
diff --git a/requirements.txt b/requirements.txt
index 939997c..6cc8e86 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -6,3 +6,5 @@ pytz>=2022.7.1
 jupyter; python_version >= '3.0'
 notebook>=4.4.1; python_version >'3.0'
 pandas>=2.0.3
+matplotlib>=3.5.1
+fpdf>=1.7.2
diff --git a/tests/test_parser.py b/tests/test_parser.py
index 55d4ef8..d00f577 100644
--- a/tests/test_parser.py
+++ b/tests/test_parser.py
@@ -2,6 +2,8 @@
 import logging
 import pandas as pd
 from parser import main
+from fpdf import FPDF
+import os
 
 class TestParser(unittest.TestCase):
 
@@ -10,10 +12,12 @@ def setUp(self):
         self.log_file = 'parser.log'
         self.csv_file = 'minhaReq2.20220126.csv'
         self.df = pd.read_csv(self.csv_file)
+        self.pdf_file = 'report.pdf'
 
     def tearDown(self):
         # Clean up after tests
-        pass
+        if os.path.exists(self.pdf_file):
+            os.remove(self.pdf_file)
 
     def test_script_execution(self):
         # Test the execution of the parser script
@@ -49,5 +53,27 @@ def test_data_analysis(self):
         self.assertEqual(len(dailymovers), 20)
         self.assertIn('ticker', dailymovers.columns)
 
+    def test_pdf_generation(self):
+        # Test the PDF report generation
+        main()
+        self.assertTrue(os.path.exists(self.pdf_file))
+
+        # Check if the PDF contains expected data
+        pdf = FPDF()
+        pdf.add_page()
+        pdf.set_font("Arial", size=12)
+        pdf.output(self.pdf_file)
+
+        with open(self.pdf_file, 'rb') as pdf_file:
+            content = pdf_file.read()
+            self.assertIn(b'Top 20 Daily Movers', content)
+            self.assertIn(b'Top 20 Daily Losers', content)
+            self.assertIn(b'Top 20 Medium Term Price Change (Growth)', content)
+            self.assertIn(b'Top 20 Medium Term Price Change (Loss)', content)
+            self.assertIn(b'Growth Potential Based on Analyst Recommendations', content)
+            self.assertIn(b'Top 20 Financial Exposure', content)
+            self.assertIn(b'Top 20 Return on Invested Capital', content)
+            self.assertIn(b'Top 20 Fundamental Data', content)
+
 if __name__ == '__main__':
     unittest.main()