Testing XML News this is the descripton string http://community-links.googlecode.com/svn/icons/news-icon.png http://community-links.googlecode.com/svn/icons/news-fanart.jpg 04.01.2013 divingmule, Johnny Cache *** updated $doregex[info] *** $doregex[refresh] refresh info $pyFunction: time.strftime('%d/%m/%Y') True ignoreme Greek Movies $doregex[makelist0] makelist0 [makelist0.param1] $doregex[makelist] ]]> (\d{4})]]> https://greeksubsmovies.me/?filter=movie&sort=recent&f_language=en&page=1 Mozilla/5.0 (Windows NT 10.0; Win64; x64) Chrome/143.0.0.0 Safari/537.36 makelist [makelist.param3] $doregex[play_movie_dialog] [makelist.param2] video ]]> \s*]*>\s*
\s*
([^<]+)<' all_movies = [] for page_num in [1, 2]: url = "https://greeksubsmovies.me/?filter=greek_movies&sort=recent&f_year=%s&f_language=el&page=%s" % (year, page_num) try: req = urllib.request.Request(url, headers=headers) with urllib.request.urlopen(req, timeout=8) as resp: html = resp.read().decode('utf-8', errors='ignore') matches = re.findall(pattern, html) if matches: all_movies.extend(matches) except: pass return all_movies ]]> Mozilla/5.0 (Windows NT 10.0; Win64; x64) Chrome/143.0.0.0 Safari/537.36 play_movie_dialog ) links = re.findall(r' https://greeksubsmovies.me[makelist.param1] Mozilla/5.0 (Windows NT 10.0; Win64; x64) Chrome/143.0.0.0 Safari/537.36 greekjar Greek Movies Youtube ignorme plugin://plugin.video.youtube/kodion/search/query/?q=Greek%20Movies https://pbs.twimg.com/profile_images/1368540629/GreekTV_logo.png Greek Movies Test 01 $doregex[makelist0] makelist0 [makelist0.param1] $doregex[makelist] ]]> (\d{4})]]> https://greeksubsmovies.net/?filter=movie&sort=recent&f_language=en&page=1 Mozilla/5.0 (Windows NT 10.0; Win64; x64) Chrome/143.0.0.0 Safari/537.36 makelist [makelist.param3] $doregex[play_movie_dialog] [makelist.param2] video ]]> \s*]*>\s*
\s*
([^<]+)<' all_movies = [] max_pages = 1 try: # 1. Fetch Page 1 to inspect pagination container first_url = "https://greeksubsmovies.net/?filter=greek_movies&sort=recent&f_year=%s&f_language=el&page=1" % year req = urllib.request.Request(first_url, headers=headers) with urllib.request.urlopen(req, timeout=8) as resp: html = resp.read().decode('utf-8', errors='ignore') # Extract movies from page 1 matches = re.findall(pattern, html) if matches: all_movies.extend(matches) # 2. Parse pagination block to find the total page count dynamically pager_match = re.search(r'', html, re.DOTALL) if pager_match: pager_html = pager_match.group(1) # Find all page numbers inside the pager links/spans page_numbers = re.findall(r'>(\d+)<', pager_html) if page_numbers: max_pages = int(page_numbers[-1]) # 3. Loop through remaining pages if more than 1 page exists for page_num in range(2, max_pages + 1): url = "https://greeksubsmovies.net/?filter=greek_movies&sort=recent&f_year=%s&f_language=el&page=%s" % (year, page_num) try: req = urllib.request.Request(url, headers=headers) with urllib.request.urlopen(req, timeout=8) as resp: html = resp.read().decode('utf-8', errors='ignore') matches = re.findall(pattern, html) if matches: all_movies.extend(matches) except Exception: pass except Exception: pass return all_movies ]]> Mozilla/5.0 (Windows NT 10.0; Win64; x64) Chrome/143.0.0.0 Safari/537.36 play_movie_dialog ) links = re.findall(r' https://greeksubsmovies.net[makelist.param1] Mozilla/5.0 (Windows NT 10.0; Win64; x64) Chrome/143.0.0.0 Safari/537.36 greekjar