'
# Find movie titles
movie_titles = []
all_text = response
# Extract movie titles by finding patterns in the text
# Look for patterns like "Title: Movie Name" or "Movie Name (Year)"
title_pattern = r'Title:\s*(.*?)(?:\n|$)'
year_pattern = r'(\b[A-Z][^()\n]*?)\s*\(\d{4}\)'
title_matches = re.findall(title_pattern, all_text)
year_matches = re.findall(year_pattern, all_text)
# Combine found titles, prioritizing explicit "Title:" format
potential_titles = title_matches + year_matches
# If we found fewer titles than posters, use a more aggressive approach
if len(potential_titles) < len(poster_urls):
# Try to extract titles from the text chunks between poster URLs
# This looks for the first line or something that looks like a title
for i, part in enumerate(parts):
if i < len(poster_urls): # Make sure we don't go beyond available posters
lines = part.strip().split('\n')
if lines:
# Get the first non-empty line as a potential title
for line in lines:
line = line.strip()
if line:
# Skip lines that look like descriptions
if len(line) < 100 and not line.startswith(("- ", "âĸ ")):
potential_titles.append(line)
break
# Fill in missing titles if needed
while len(potential_titles) < len(poster_urls):
potential_titles.append(f"Movie {len(potential_titles) + 1}")
# Process each poster
for i in range(len(poster_urls)):
title = "Movie" # Default title
# Use the extracted title if available
if i < len(potential_titles):
title = potential_titles[i]
html_output += f"""
{title}
"""
html_output += '