import os
import re
from collections import defaultdict
from bs4 import BeautifulSoup
import time
start = time.time()
def search_and_count_terms_in_files(root_folder, text_terms, tag_terms, output_file):
# Compile the regular expressions for the text terms
text_patterns = [re.compile(term) for term in text_terms]
# Dictionary to store the counts of each text term
text_term_counts = defaultdict(int)
# Dictionary to store the counts of each tag term
tag_term_counts = defaultdict(int)
# Dictionary to store the counts of each text term in each file
file_text_term_counts = defaultdict(lambda: defaultdict(int))
# Dictionary to store the counts of each tag term in each file
file_tag_term_counts = defaultdict(lambda: defaultdict(int))
# Walk through the directory
for dirpath, dirnames, filenames in os.walk(root_folder):
for filename in filenames:
if filename.endswith('.html'):
file_path = os.path.join(dirpath, filename)
try:
with open(file_path, 'r', encoding='utf-8') as file:
content = file.read()
soup = BeautifulSoup(content, 'html.parser')
p_tags = soup.find_all('p')
# Count text terms
for p in p_tags:
p_text = p.get_text()
for pattern in text_patterns:
count = len(pattern.findall(p_text))
if count > 0:
text_term_counts[pattern.pattern] += count
file_text_term_counts[pattern.pattern][file_path] += count
# Count tag terms
for tag in tag_terms:
tag_count = len(soup.find_all(tag))
if tag_count > 0:
tag_term_counts[tag] += tag_count
file_tag_term_counts[tag][file_path] += tag_count
except Exception as e:
print(f"Error reading file {file_path}: {e}")
# Open the output file in write mode
with open(output_file, 'w', encoding='utf-8') as html_file:
html_file.write("\n")
html_file.write("Search and Count Results
\n")
# Write the total counts of each text term to the HTML file
html_file.write("Text Terms:
\n")
for term, count in text_term_counts.items():
html_file.write(f"'{term}': {count}
\n")
sorted_files = sorted(file_text_term_counts[term].items(), key=lambda x: x[1], reverse=True)
html_file.write("\n")
for file_path, file_count in sorted_files:
html_file.write(f"- Found {file_count} times in file: {file_path}
\n")
html_file.write("
\n")
# Write the total counts of each tag term to the HTML file
html_file.write("Tag Terms:
\n")
for term, count in tag_term_counts.items():
html_file.write(f"'{term}': {count}
\n")
sorted_files = sorted(file_tag_term_counts[term].items(), key=lambda x: x[1], reverse=True)
html_file.write("\n")
for file_path, file_count in sorted_files:
html_file.write(f"- Found {file_count} times in file: {file_path}
\n")
html_file.write("
\n")
html_file.write("\n")
# Define the text terms to search for
text_terms_to_search = ["वन्दनीया माताजी", "माताजी", "पूज्य गुरुदेव", "गुरुदेव", "पूज्य गुरुजी", "पूज्य गुरुजी", "शान्तिकुञ्ज", "क्रान्तिधर्मी", "गायत्री साधना", "आत्मबोध", "तत्त्वबोध", "गायत्री मंत्र", "युगऋषि", "युग ऋषि", "ऋषि", "युग निर्माण", "विचार क्रान्ति", "महाकाल", "बलिवैश्व"]
# Define the tag terms to search for
tag_terms_to_search = ["div", "p", "br", "a"]
# Define the root folder of the static website
root_folder = './'
# Define the output HTML file
output_file = 'find-count-words-lechat-mistral.html'
# Call the function to search for and count the terms
search_and_count_terms_in_files(root_folder, text_terms_to_search, tag_terms_to_search, output_file)
print("Output file is saved as find-count-words-lechat-mistral.html")
end = time.time()
print("Elapsed (with compilation) = %s" % (end - start))