nyaa.pantsu.cat update

NyaaPy/nyaapantsu.py

@@ -5,38 +5,30 @@ from NyaaPy.utils import Utils as utils
 
 class NyaaPantsu():
     '''
-     Make a query to nyaa.pantsu.cat using keyword as keyword.
-     Returns an array of OrderedDict with every result of the query.
-     Returns an empty array if no results.
+     Return a list of dicts with the results of the query.
     '''
-    def search(keyword):
-        nyaapantsu_baseurl = "https://nyaa.pantsu.cat/feed?c=_&s=0&max=99999&userID=0&q="
+    def search(keyword, category, subcategory, filters, page):
+        if page > 0:
+            r = requests.get("http://nyaa.pantsu.cat/?f={}&c={}_{}&q={}&p={}".format(filters, category, subcategory, keyword, page))
+        else:
+            r = requests.get("http://nyaa.pantsu.cat/?f={}&c={}_{}&q={}".format(filters, category, subcategory, keyword))
 
-        request  = requests.get(nyaa_baseurl + keyword)
-        response = xmltodict.parse(request.text)
+        soup = BeautifulSoup(r.text, 'html.parser')
+        rows = soup.select('table tr')
 
-        results = []
+        results = {}
 
-        try:
-            if type(response['rss']['channel']['item']) is collections.OrderedDict:
-                results.append(response['rss']['channel']['item'])
-            else:
-                results = response['rss']['channel']['item']
-
-        except KeyError as ex:
-            results = []
+        if rows:
+            results = utils.parse_pantsu(rows, limit=None)
 
         return results
-
+    
     '''
-     Returns an array of OrderedDict with the n last updates of nyaa.pantsu.cat
+     Returns an array of dicts with the n last updates of Nyaa.si
     '''
-    def news(n):
-        nyaa_baseurl = "https://nyaa.pantsu.cat/feed"
+    def news(number_of_results):
+        r = requests.get("http://nyaa.pantsu.cat/")
+        soup = BeautifulSoup(r.text, 'html.parser')
+        rows = soup.select('table tr')
 
-        request  = requests.get(nyaa_baseurl)
-        response = xmltodict.parse(request.text)
-
-        results = response['rss']['channel']['item']
-
-        return results[:n]
+        return utils.parse_pantsu(rows, limit=number_of_results)

NyaaPy/utils.py

@@ -4,7 +4,7 @@
 
 class Utils():
 
-    def get_categories(b):
+    def nyaa_categories(b):
         c = b.replace('/?c=', '')
         cats = c.split('_')
 
@@ -68,6 +68,15 @@ class Utils():
 
         return category_name
 
+    def pantsu_categories(b):
+        c = b.replace('/search?c=', '')
+        cats = c.split('_')
+
+        cat = cats[0]
+        subcat = cats[1]
+
+        return "{} - {}".format(cat, subcat)
+
     def parse_nyaa(table_rows, limit):
 
         torrents = []
@@ -88,7 +97,7 @@ class Utils():
 
                 try:
                     torrent = {
-                        'category': Utils.get_categories(block[0]),
+                        'category': Utils.nyaa_categories(block[0]),
                         'url': "http://nyaa.si{}".format(block[1]),
                         'name': block[2],
                         'download_url': "http://nyaa.si{}".format(block[4]),
@@ -104,4 +113,42 @@ class Utils():
                 except IndexError as ie:
                     pass
         
+        return torrents
+
+    def parse_pantsu(table_rows, limit):
+
+        torrents = []
+
+        limit = limit + 1
+
+        for row in table_rows[1:limit]:
+            block = []
+                
+            for td in row.find_all('td'):
+                if td.find_all('a'):
+                    for link in td.find_all('a'):
+                        if "lang" not in link.get('href'):
+                            block.append(link.get('href'))
+
+                if td.text.rstrip():
+                    block.append(td.text.replace('\n', ''))
+                    
+            try:
+                torrent = {
+                    'category': Utils.pantsu_categories(block[0]),
+                    'url': "http://nyaa.pantsu.cat{}".format(block[1]),
+                    'name': block[2],
+                    'download_url': block[4],
+                    'magnet': block[3],
+                    'size': block[5],
+                    'date': block[9],
+                    'seeders': block[6],
+                    'leechers': block[7],
+                    'completed_downloads': block[8],
+                }
+            
+                torrents.append(torrent)
+            except IndexError as ie:
+                pass
+        
         return torrents