#!/usr/bin/env python
import os
import re
import time
from bs4 import BeautifulSoup
start = time.time()
def search_words(root_dir, words, output_file):
if os.path.exists(output_file):
os.remove(output_file)
html = "Search Results
"
html += ""
html += ""
html += ""
html += ""
html += ""
html += ""
html += ""
words = [word.strip() 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)
for root, dirs, files in os.walk(root_dir):
# if'search' in root: # replace 'dir_to_exclude' with the actual directory name
# continue
for file in files:
if file.endswith('.html'):
file_path = os.path.join(root, file)
relative_path = os.path.relpath(file_path, output_dir)
relative_path = './' + relative_path
try:
with open(file_path, 'r') as f:
content = f.read()
soup = BeautifulSoup(content, 'html.parser')
title = soup.find('title')
if title:
title_text = title.text.strip()
title_text = title_text.replace('(गायत्री परिवार - Gayatri Pariwar)', '')
else:
title_text = file
p_elements = soup.find_all('p')
for p in p_elements:
p_text = p.get_text()
p_words = p_text.split()
indices = []
for word in words:
indices.append([i for i, x in enumerate(p_words) if x.lower().find(word.lower())!= -1])
for idx_list in indices[0]:
if all(any(abs(idx_list - idx) <= 100 for idx in idxs) for idxs in indices[1:]):
start = idx_list - 9
end = idx_list + 9 + 1
if start < 0:
start = 0
if end > len(p_words):
end = len(p_words)
snippet =' '.join(p_words[start:end])
bolded_snippet = snippet
for word in words:
bolded_snippet = bolded_snippet.replace(word, f"{word}")
results.append((title_text, relative_path, bolded_snippet, len([w for w in words if w in bolded_snippet]), p_text))
except Exception as e:
print(f"Error reading {file_path}: {e}")
exact_matches = [result for result in results if result[3] == len(words)]
exact_matches.sort(key=lambda x: tuple(x[2].lower().find(word.lower()) for word in words))
exact_matches = exact_matches[:100]
for title_text, relative_path, snippet, _, p_text in exact_matches:
title = snippet +' '+ p_text[p_text.find(snippet) + len(snippet):].strip()
stop_chars = ['।','?','॥','.']
title_end_index = len(snippet) + 315
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 += f"- {title_text} - {snippet}
"
html += "
Partial Matches
"
partial_matches = [result for result in results if result[3]!= len(words)]
partial_matches.sort(key=lambda x: sum([words.index(word) for word in x[2].split() if word in words]), reverse=True)
partial_matches = partial_matches[:5]
for title_text, relative_path, snippet, _, p_text in partial_matches:
title = snippet +' '+ p_text[p_text.find(snippet) + len(snippet):].strip()
stop_chars = ['।','?','॥','.']
title_end_index = len(snippet) + 315
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()
html += f"- {title_text} - {snippet}
"
html += "
"
output_path = os.path.join(search_dir, output_file)
with open(output_path, 'w') as f:
f.write(html)
print(html)
root_dir = '../'
words = 'अध्यात्म,क्या,है'
output_file ='search_multiple_words.html'
# search_words(root_dir, words, output_file)
print("See "+output_file)
end = time.time()
print("Elapsed (with compilation) = %s" % (end - start))