import os
import re
import time
from bs4 import BeautifulSoup
from concurrent.futures import ThreadPoolExecutor
def process_file(file_path, words_set, output_dir, results, phrase):
try:
with open(file_path, 'r') as f:
content = f.read()
soup = BeautifulSoup(content, 'html.parser')
title = soup.find('title')
title_text = title.text.strip() if title else os.path.basename(file_path)
title_text = title_text.replace('(गायत्री परिवार - Gayatri Pariwar)', '')
p_elements = soup.find_all('p')
for p in p_elements:
p_text = p.get_text()
sentences = re.split(r'([।?॥])', p_text)
for i in range(0, len(sentences), 2):
sentence = sentences[i]
delimiter = sentences[i + 1] if i + 1 < len(sentences) else ''
if all(word in sentence.lower() for word in phrase.lower().split()):
start_idx = max(0, i - 4) # Include 2-3 more sentences before
end_idx = min(len(sentences), i + 5) # Include 2-3 more sentences after
context_sentences = sentences[start_idx:end_idx]
bolded_sentence = ' '.join(context_sentences[0::2]) + ' '.join(context_sentences[1::2])
for word in phrase.lower().split():
bolded_sentence = re.sub(r'(' + re.escape(word) + r')', r'\1', bolded_sentence, flags=re.IGNORECASE)
results.append((title_text, os.path.relpath(file_path, output_dir), bolded_sentence, len([w for w in words_set if w in bolded_sentence]), p_text))
except Exception as e:
print(f"Error reading {file_path}: {e}")
def search_words(root_dir, words, output_file, phrase):
if os.path.exists(output_file):
os.remove(output_file)
html_parts = [
"Search Results
",
"",
"",
f"",
"",
"",
"",
""
]
words_set = set(word.strip().lower() for word in words.split(','))
results = []
output_dir = os.path.dirname(__file__)
search_dir = os.path.join(output_dir)
if not os.path.exists(search_dir):
os.makedirs(search_dir)
with ThreadPoolExecutor(max_workers=4) as executor:
futures = []
for root, _, files in os.walk(root_dir):
for file in files:
if file.endswith('.html'):
file_path = os.path.join(root, file)
futures.append(executor.submit(process_file, file_path, words_set, output_dir, results, phrase))
for future in futures:
future.result()
# Prioritize exact matches
exact_matches = sorted(
(result for result in results if all(word in result[2].lower() for word in phrase.lower().split())),
key=lambda x: tuple(x[2].lower().find(word) for word in words_set)
)
# Prioritize nearby matches within the same sentence
nearby_matches = sorted(
(result for result in results if not all(word in result[2].lower() for word in phrase.lower().split()) and all(word in result[2].lower() for word in words_set)),
key=lambda x: min(x[2].lower().find(word) for word in words_set)
)
for title_text, relative_path, snippet, _, p_text in exact_matches + nearby_matches:
title = snippet + ' ' + p_text[p_text.find(snippet) + len(snippet):].strip()
stop_chars = ['।', '?', '॥', '.']
title_end_index = len(snippet) + 115
for char in stop_chars:
index = title[:title_end_index].rfind(char)
if index != -1:
title_end_index = index + 1
break
title = title[:title_end_index].strip()
title = re.sub('<.*?>', '', title)
html_parts.append(f"- {title_text} - {snippet}
")
html_parts.append("
")
output_path = os.path.join(search_dir, output_file)
with open(output_path, 'w') as f:
f.write(''.join(html_parts))
print(''.join(html_parts))
def sort_html_file(input_file_name, output_file_name, phrase):
try:
with open(input_file_name, 'r', encoding='utf-8', errors='ignore') as f:
html = f.read()
print("HTML loaded successfully")
# Find all links and descriptions
links_and_descriptions = re.findall(r'.*?<\/li>', html, re.DOTALL)
print("Links and descriptions found:", len(links_and_descriptions))
# Extract link and description from each item
extracted_links_and_descriptions = []
for item in links_and_descriptions:
match = re.search(r'href=[\'"]([^\'"]+)[\'"]', item)
if match:
link = match.group(1)
match = re.search(r'>[^<]+?<\/a>', item)
if match:
title = match.group(0)[1:-4]
description = re.sub(r'<.*?>', '', item).strip().split('-', 1)[1].strip()
extracted_links_and_descriptions.append((link, title, description))
print("Extracted links and descriptions:", len(extracted_links_and_descriptions))
# Sort links and descriptions based on the presence of the phrase
phrase_links_and_descriptions = [x for x in extracted_links_and_descriptions if all(word in x[2].lower() for word in phrase.lower().split())]
sorted_phrase_links_and_descriptions = sorted(phrase_links_and_descriptions, key=lambda x: sum(x[2].lower().find(word) for word in phrase.lower().split()))
sorted_links_and_descriptions = []
words = phrase.split()
added_descriptions = set()
for link, title, description in sorted_phrase_links_and_descriptions:
# Highlight each word if they appear in any combination within the same sentence
for word in phrase.lower().split():
description = re.sub(r'(' + re.escape(word) + r')', r'\1', description, flags=re.IGNORECASE)
description_words = description.split()
description_hash = tuple(sorted(description_words[:7])) # Use the first 7 words as a hash
if description_hash not in added_descriptions:
sorted_links_and_descriptions.append((link, title, description))
added_descriptions.add(description_hash)
print("Links and descriptions sorted")
# Create the sorted HTML
sorted_html = 'Search Results
'
sorted_html += ''
sorted_html += ''
sorted_html += f""
sorted_html += ''
sorted_html += ''
sorted_html += ''
sorted_html += ''
for link, title, description in sorted_links_and_descriptions:
sorted_html += f'- {title} - {description}
'
sorted_html += '
'
print("Sorted HTML created")
# Save the sorted HTML to the output file
with open(output_file_name, 'w', encoding='utf-8', errors='ignore') as f:
f.write(sorted_html)
print("Sorted HTML saved to output file as", output_file_name)
except Exception as e:
print("An error occurred:", str(e))
def get_user_input():
return input("Enter the phrase to search: ")
# Usage example
start = time.time()
root_dir = '../' # Adjust as needed
phrase = get_user_input()
words = ','.join(phrase.split())
output_file = 'search_multiple_words.html'
search_words(root_dir, words, output_file, phrase)
sort_html_file(output_file, 'sorted_search_results.html', phrase)
# Create the final HTML file
with open('search-phrase.html', 'w', encoding='utf-8') as f:
f.write('')
f.write('आपकी महत्त्वपूर्ण जिज्ञासाएँ - पूज्य गुरुसत्ता के समाधान
')
f.write("')
print('search-phrase.html created successfully')
end = time.time()
print("Elapsed (with compilation) = %s" % (end - start))