Nyaa.si & sukebei.nyaa.si LXML fully ready

.gitignore

@@ -3,4 +3,5 @@ dist/
 nyaapy.egg-info
 .vscode
 env/
-*.pyc
+*.pyc
+test_files

NyaaPy/nyaa.py

@@ -1,12 +1,11 @@
 import requests
-import urllib.parse
 from NyaaPy import utils
 
 
 class Nyaa:
 
     def __init__(self):
-        self.URI = "http://nyaa.si"
+        self.URI = "https://nyaa.si"
 
     def last_uploads(self, number_of_results):
         r = requests.get(self.URI)

NyaaPy/sukebei.py

@@ -1,8 +1,12 @@
 import requests
-from bs4 import BeautifulSoup
 from NyaaPy import utils
 
+
 class SukebeiNyaa:
+
+    def __init__(self):
+        self.URI = "https://sukebei.nyaa.si"
+
     def search(self, keyword, **kwargs):
         category = kwargs.get('category', 0)
         subcategory = kwargs.get('subcategory', 0)
@@ -11,37 +15,37 @@ class SukebeiNyaa:
 
         if page > 0:
             r = requests.get("{}/?f={}&c={}_{}&q={}&p={}".format(
-                "http://sukebei.nyaa.si", filters, category, subcategory,
+                self.URI, filters, category, subcategory,
                 keyword, page))
         else:
             r = requests.get("{}/?f={}&c={}_{}&q={}".format(
-                "http://sukebei.nyaa.si", filters, category, subcategory,
+                self.URI, filters, category, subcategory,
                 keyword))
 
-        soup = BeautifulSoup(r.text, 'html.parser')
-        rows = soup.select('table tr')
-
-        return utils.parse_nyaa(rows, limit=None)
+        r.raise_for_status()
+        return utils.parse_nyaa(r.text, limit=None, sukebei=True)
 
     def get(self, id):
-        r = requests.get("http://sukebei.nyaa.si/view/{}".format(id))
-        soup = BeautifulSoup(r.text, 'html.parser')
-        content = soup.findAll("div", {"class": "panel", "id": None})
+        r = requests.get("{}/view/{}".format(self.URI, id))
+        r.raise_for_status()
 
-        return utils.parse_single(content)
+        return utils.parse_single(r.text, sukebei=True)
 
     def get_user(self, username):
-        r = requests.get("http://sukebei.nyaa.si/user/{}".format(username))
-        soup = BeautifulSoup(r.text, 'html.parser')
+        r = requests.get("{}/user/{}".format(self.URI, username))
+        r.raise_for_status()
 
-        return utils.parse_nyaa(soup.select('table tr'), limit=None)
+        return utils.parse_nyaa(r.text, limit=None, sukebei=True)
 
-    def news(self, number_of_results):
-        r = requests.get("http://sukebei.nyaa.si/")
-        soup = BeautifulSoup(r.text, 'html.parser')
-        rows = soup.select('table tr')
+    def last_uploads(self, number_of_results):
+        r = requests.get(self.URI)
+        r.raise_for_status()
 
-        return utils.parse_sukebei(rows, limit=number_of_results + 1)
+        return utils.parse_nyaa(
+            r.text,
+            limit=number_of_results + 1,
+            sukebei=True
+        )
 
 
 class SukebeiPantsu:

NyaaPy/utils.py

@@ -72,10 +72,15 @@ def nyaa_categories(b):
     return category_name
 
 
-def parse_nyaa(request_text, limit):
+def parse_nyaa(request_text, limit, sukebei=False):
     parser = etree.HTMLParser()
     tree = etree.fromstring(request_text, parser)
 
+    if sukebei is False:
+        uri = "https://nyaa.si"
+    else:
+        uri = "https://sukebei.nyaa.si"
+
     torrents = []
 
     # Going through table rows
@@ -109,10 +114,10 @@ def parse_nyaa(request_text, limit):
         try:
             torrent = {
                 'id': block[1],
-                'category': nyaa_categories(block[0]),
-                'url': "https://nyaa.si/view/{}".format(block[1]),
+                'category': nyaa_categories(block[0]) if sukebei is False else sukebei_categories(block[0]),
+                'url': "{}/view/{}".format(uri, block[1]),
                 'name': block[2],
-                'download_url': "https://nyaa.si/download/{}".format(block[3]),
+                'download_url': "{}/download/{}".format(uri, block[3]),
                 'magnet': block[4],
                 'size': block[5],
                 'date': block[6],
@@ -127,10 +132,15 @@ def parse_nyaa(request_text, limit):
     return torrents
 
 
-def parse_single(request_text):
+def parse_single(request_text, sukebei=False):
     parser = etree.HTMLParser()
     tree = etree.fromstring(request_text, parser)
 
+    if sukebei is False:
+        uri = "https://nyaa.si"
+    else:
+        uri = "https://sukebei.nyaa.si"
+
     torrent = {}
     data = []
     torrent_files = []
@@ -152,7 +162,7 @@ def parse_single(request_text):
         tree.xpath("//h3[@class='panel-title']/text()")[0].strip()
     torrent['category'] = data[0]
     torrent['uploader'] = data[4]
-    torrent['uploader_profile'] = "http://nyaa.si/user/{}".format(data[4])
+    torrent['uploader_profile'] = "{}/user/{}".format(uri, data[4])
     torrent['website'] = data[6]
     torrent['size'] = data[8]
     torrent['date'] = data[3]
@@ -169,49 +179,8 @@ def parse_single(request_text):
     return torrent
 
 
-def parse_sukebei(table_rows, limit):
-    if limit == 0:
-        limit = len(table_rows)
-
-    torrents = []
-
-    for row in table_rows[:limit]:
-        block = []
-
-        for td in row.find_all('td'):
-            for link in td.find_all('a'):
-                if link.get('href')[-9:] != '#comments':
-                    block.append(link.get('href'))
-                    block.append(link.text.rstrip())
-
-            if td.text.rstrip():
-                block.append(td.text.rstrip())
-
-            try:
-                torrent = {
-                    'id': block[1].replace("/view/", ""),
-                    'category': sukebei_categories(block[0]),
-                    'url': "http://sukebei.nyaa.si{}".format(block[1]),
-                    'name': block[2],
-                    'download_url': "http://sukebei.nyaa.si{}".format(
-                        block[4]),
-                    'magnet': block[5],
-                    'size': block[6],
-                    'date': block[7],
-                    'seeders': block[8],
-                    'leechers': block[9],
-                    'completed_downloads': block[10],
-                }
-            except IndexError as ie:
-                pass
-
-            torrents.append(torrent)
-
-    return torrents
-
-
 def sukebei_categories(b):
-    c = b.replace('/?c=', '')
+    c = b.replace('?c=', '')
     cats = c.split('_')
 
     cat = cats[0]

tests/test.py

@@ -1,40 +1,51 @@
-from NyaaPy import Pantsu, Nyaa
+from NyaaPy import Nyaa
 from pprint import pprint
 from datetime import datetime
+import json
+import sys
+import os
+
+# Creating a folder for test_files
+# ! not included in github project.
+if not os.path.isdir("test_files"):
+    os.makedirs("test_files")
 
-# pantsu = Pantsu()
 nyaa = Nyaa()
 
 # Get fresh torrents
 dt_latest_torrents_begin = datetime.now()
 latest_torrents = nyaa.last_uploads(100)
 dt_latest_torrents_end = datetime.now()
+with open("test_files/nyaa_latest_torrent_test.json", 'w') as f:
+    json.dump(latest_torrents, f)
 
-# I'd like to watch Tenki no ko, but not uploaded yet.
+# Search some nasty stuff
 dt_search_begin = datetime.now()
-test_search = nyaa.search("Kimi no Na wa")
+test_search = nyaa.search("kimi no na wa")
 dt_search_end = datetime.now()
-# pprint(test_search)
+with open("test_files/nyaa_search_test.json", 'w') as f:
+    json.dump(test_search, f)
 
 # Get first torrent from found torrents
-# print("First result torrent info:")
 dt_single_torrent_begin = datetime.now()
 single_torrent = nyaa.get(test_search[0]["id"])
 dt_single_torrent_end = datetime.now()
-#pprint(single_torrent)
+with open("test_files/nyaa_single_torrent_test.json", 'w') as f:
+    json.dump(single_torrent, f)
 
 dt_user_begin = datetime.now()
-user_torrents = nyaa.get_user("Lilith-Raws")
+user_torrents = nyaa.get_user("HorribleSubs")
 dt_user_end = datetime.now()
-#pprint(user_torrents)
+with open("test_files/nyaa_single_user_test.json", 'w') as f:
+    json.dump(user_torrents, f)
 
 print(
     "Latest torrents time:",
     (dt_latest_torrents_end - dt_latest_torrents_begin).microseconds / 1000,
     "msec")
 print(
-    "Test search time:", 
-    (dt_search_end - dt_search_begin).microseconds/ 1000,
+    "Test search time:",
+    (dt_search_end - dt_search_begin).microseconds / 1000,
     "msec"
 )
 print(
@@ -44,11 +55,6 @@ print(
 )
 print(
     "Single user time:",
-    (dt_user_end - dt_user_begin ).microseconds / 1000, 
+    (dt_user_end - dt_user_begin).microseconds / 1000,
     "msec"
 )
-
-"""
-print(pantsu.search(keyword='koe no katachi',
-                    lang=["es", "ja"], category=[1, 3]))
-"""

tests/test_sukebei.py

@@ -0,0 +1,60 @@
+from NyaaPy import SukebeiNyaa
+from pprint import pprint
+from datetime import datetime
+import json
+import sys
+import os
+
+# Creating a folder for test_files
+# ! not included in github project.
+if not os.path.isdir("test_files"):
+    os.makedirs("test_files")
+
+nyaa = SukebeiNyaa()
+
+# Get fresh torrents
+dt_latest_torrents_begin = datetime.now()
+latest_torrents = nyaa.last_uploads(100)
+dt_latest_torrents_end = datetime.now()
+with open("test_files/sukebei_latest_torrent_test.json", 'w') as f:
+    json.dump(latest_torrents, f)
+
+# Search some nasty stuff
+dt_search_begin = datetime.now()
+test_search = nyaa.search("G Senjou no maou")
+dt_search_end = datetime.now()
+with open("test_files/sukebei_search_test.json", 'w') as f:
+    json.dump(test_search, f)
+
+# Get first torrent from found torrents
+dt_single_torrent_begin = datetime.now()
+single_torrent = nyaa.get(test_search[0]["id"])
+dt_single_torrent_end = datetime.now()
+with open("test_files/sukebei_single_torrent_test.json", 'w') as f:
+    json.dump(single_torrent, f)
+
+dt_user_begin = datetime.now()
+user_torrents = nyaa.get_user("RUNBKK")
+dt_user_end = datetime.now()
+with open("test_files/sukebei_single_user_test.json", 'w') as f:
+    json.dump(user_torrents, f)
+
+print(
+    "Latest torrents time:",
+    (dt_latest_torrents_end - dt_latest_torrents_begin).microseconds / 1000,
+    "msec")
+print(
+    "Test search time:",
+    (dt_search_end - dt_search_begin).microseconds / 1000,
+    "msec"
+)
+print(
+    "Single torrent time:",
+    (dt_single_torrent_end - dt_single_torrent_begin).microseconds / 1000,
+    "msec"
+)
+print(
+    "Single user time:",
+    (dt_user_end - dt_user_begin).microseconds / 1000,
+    "msec"
+)