Merge pull request #11 from JuanjoSalvador/version-0.4

Version 0.4

.gitignore

@@ -1,3 +1,4 @@
 build/
 dist/
 nyaapy.egg-info
+.vscode

NyaaPy/__init__.py

@@ -0,0 +1,10 @@
+# Info about the module
+__version__   = '0.4.1'
+__author__    = 'Juanjo Salvador'
+__email__     = 'juanjosalvador@netc.eu'
+__url__       = 'http://juanjosalvador.me'
+__copyright__ = '2017 Juanjo Salvador'
+__license__   = 'MIT license'
+
+from NyaaPy.nyaa import Nyaa
+from NyaaPy.nyaapantsu import NyaaPantsu

NyaaPy/nyaa.py

@@ -1,47 +1,33 @@
 import requests
-import xmltodict
+from bs4 import BeautifulSoup
-import json
+from NyaaPy.utils import Utils as utils
-import collections
 
 class Nyaa():
-    def search(keyword, page):
+    '''
-        if not page:
+     Return a list of dicts with the results of the query.
-            url  = "https://nyaa.si/?page=rss&c=1_0&f=0&q={}".format(keyword)
+    '''
+    def search(keyword, category, subcategory, filters, page):
+        if page > 0:
+            r = requests.get("http://nyaa.si/?f={}&c={}_{}&q={}&p={}".format(filters, category, subcategory, keyword, page))
         else:
-            url  = "https://nyaa.si/?page=rss&c=1_0&f=0&q={}&p={}".format(keyword, page)
+            r = requests.get("http://nyaa.si/?f={}&c={}_{}&q={}".format(filters, category, subcategory, keyword))
 
-        request  = requests.get(url)
+        soup = BeautifulSoup(r.text, 'html.parser')
-        response = xmltodict.parse(request.text)
+        rows = soup.select('table tr')
 
-        results  = []
+        results = {}
 
-        try:
+        if rows:
-            if type(response['rss']['channel']['item']) is collections.OrderedDict:
+            results = utils.parse_nyaa(rows, limit=None)
-                results.append(response['rss']['channel']['item'])
-            else:
-                results = response['rss']['channel']['item']
-
-        except KeyError as ex:
-            results = []
 
         return results
     
-class NyaaPantsu():
+    '''
-    def search(keyword):
+     Returns an array of dicts with the n last updates of Nyaa.si
-        nyaapantsu_baseurl = "https://nyaa.pantsu.cat/feed?c=_&s=0&max=99999&userID=0&q="
+    '''
+    def news(number_of_results):
+        r = requests.get("http://nyaa.si/")
+        soup = BeautifulSoup(r.text, 'html.parser')
+        rows = soup.select('table tr')
 
-        request  = requests.get(nyaa_baseurl + keyword)
+        return utils.parse_nyaa(rows, limit=number_of_results)
-        response = xmltodict.parse(request.text)
-
-        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 = []
-
-        return results

NyaaPy/nyaapantsu.py

@@ -0,0 +1,42 @@
+import requests
+from bs4 import BeautifulSoup
+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.
+    '''
+    def search(keyword):
+        nyaapantsu_baseurl = "https://nyaa.pantsu.cat/feed?c=_&s=0&max=99999&userID=0&q="
+
+        request  = requests.get(nyaa_baseurl + keyword)
+        response = xmltodict.parse(request.text)
+
+        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 = []
+
+        return results
+
+    '''
+     Returns an array of OrderedDict with the n last updates of nyaa.pantsu.cat
+    '''
+    def news(n):
+        nyaa_baseurl = "https://nyaa.pantsu.cat/feed"
+
+        request  = requests.get(nyaa_baseurl)
+        response = xmltodict.parse(request.text)
+
+        results = response['rss']['channel']['item']
+
+        return results[:n]

NyaaPy/utils.py

@@ -0,0 +1,107 @@
+'''
+    Module utils
+'''
+
+class Utils():
+
+    def get_categories(b):
+        c = b.replace('/?c=', '')
+        cats = c.split('_')
+
+        cat = cats[0]
+        subcat = cats[1]
+
+        categories = {
+            "1": {
+                "name": "Anime",
+                "subcats": {
+                    "1": "Anime Music Video",
+                    "2": "English-translated",
+                    "3": "Non-English-translated",
+                    "4": "Raw"
+                }
+            },
+            "2": {
+                "name": "Audio",
+                "subcats": {
+                    "1": "Lossless",
+                    "2": "Lossy"
+                }
+            },
+            "3": {
+                "name": "Literature",
+                "subcats": {
+                    "1": "English-translated",
+                    "2": "Non-English-translated",
+                    "3": "Raw"
+                }
+            },
+            "4": { 
+                "name": "Live Action",
+                "subcats": {
+                    "1": "English-translated",
+                    "2": "Idol/Promotional Video",
+                    "3": "Non-English-translated",
+                    "4": "Raw"
+                }
+            },
+            "5": { 
+                "name": "Pictures",
+                "subcats": {
+                    "1": "Graphics",
+                    "2": "Photos"
+                }
+            },
+            "6": { 
+                "name": "Software",
+                "subcats": {
+                    "1": "Applications",
+                    "2": "Games"
+                }
+            }
+        }
+        
+        try:
+            category_name = "{} - {}".format(categories[cat]['name'], categories[cat]['subcats'][subcat])
+        except:
+            pass
+
+        return category_name
+
+    def parse_nyaa(table_rows, limit):
+
+        torrents = []
+
+        for row in table_rows[:limit]:
+                block = []
+
+                for td in row.find_all('td'):
+                    if td.find_all('a'):
+                        for link in td.find_all('a'):
+                            if link.get('href')[-9:] != '#comments':
+                                block.append(link.get('href'))
+                                if link.text.rstrip():
+                                    block.append(link.text)
+
+                    if td.text.rstrip():
+                        block.append(td.text.rstrip())
+
+                try:
+                    torrent = {
+                        'category': Utils.get_categories(block[0]),
+                        'url': "http://nyaa.si{}".format(block[1]),
+                        'name': block[2],
+                        'download_url': "http://nyaa.si{}".format(block[4]),
+                        'magnet': block[5],
+                        'size': block[6],
+                        'date': block[7],
+                        'seeders': block[8],
+                        'leechers': block[9],
+                        'completed_downloads': block[10],
+                    }
+                
+                    torrents.append(torrent)
+                except IndexError as ie:
+                    pass
+        
+        return torrents

README.md

@@ -2,15 +2,132 @@
 
 Unofficial Python module to search into Nyaa.si and nyaa.pantsu.cat.
 
-Based on [Kylart's Nyaapi](https://github.com/Kylart/Nyaapi).
+Supports Python 3+
+
+* [Installation](#installation)
+* [Example](#example)
+* [Methods](#methods)
+    * [search()](#search)
+    * [news()](#news)
+* [Categories and subcategories](#categories-and-subcategories)
+* [Contributions and development](#contributons-and-development)
+* [License](#license)
 
 
-### Installation and ussage
+## Installation
 
 Install it using pip.
 
     pip install nyaapy
 
+## Example
+
+```python
+    from NyaaPy import Nyaa, NyaaPantsu
+
+    nyaa_query = Nyaa.search(keyword='koe no katachi 1080', category=1, subcategory=0, filters=0, page=0)
+
+    nyaa_news = Nyaa.news(5)
+
+    if len(nyaa_query) > 0:
+        for result in nyaa_query:
+            print(result['title'])
+    else:
+        print('Nothing here!')
+
+    for new in nyaa_news:
+        print(new['title])
+```
+
+## Methods
+
+### search()
+
+Returns a list of dicts with the search results.
+
+Parameters:
+
+* **keyword**: String. Keyword for the search query.
+* **category**: Integer.
+* **subcategory**: Integer. 
+* **filters**: Integer. 
+* **page**: Integer.
+
+`page` must be between 0 and 1000.
+
+#### Dict returned for Nyaa.si
+
+```python
+    'category': "Anime - English-translated",
+    'url': "https://nyaa.si/view/968600",
+    'name': "[HorribleSubs] Shoukoku no Altair - 14 [720p].mkv",
+    'download_url': "https://nyaa.si/download/968600.torrent",
+    'magnet': <magnet torrent URI>
+    'size': "317.2 MiB",
+    'date': "2017-10-13 20:16",
+    'seeders': "538",
+    'leechers': "286",
+    'completed_downloads': "852"
+```
+
+### news()
+
+Parameters:
+
+* **number_of_results**: Integer
+
+`number_of_results` must be between 1 and 75.
+
+
+## Categories and subcategories
+
+List of available categories and subcategories:
+
+1. Anime.
+
+    1.1 - Anime Music Video
+
+    1.2 - English-translated
+
+    1.3 - Non-English-translated
+
+    1.4 - Raw
+
+2. Audio.
+
+    2.1 - Lossless
+
+    2.2 - Lossy
+
+3. Literature.
+
+    3.1 - English-translated
+
+    3.2 - Non-English-translated
+
+    3.3 - Raw
+
+4. Live Action.
+
+    4.1 - English-translated
+
+    4.2 - Idol/Promotional Video
+
+    4.3 - Non-English-translated
+
+    4.4 - Raw
+
+5. Pictures.
+
+    5.1 - Graphics
+
+    5.2 - Photos
+
+6. Software.
+
+    6.1 - Applications
+
+    6.2 - Games
 
 ### Contributions and development
 
@@ -35,28 +152,6 @@ At this moment there isn't an official Nyaa.si API, so we only can make requests
 
 4. Always use the code into `src` folder, never the package.
 
-### Example code
+## License
-
-    from NyaaPy.nyaa import Nyaa
-    from NyaaPy.nyaa import NyaaPantsu
-
-    # Nyaa.si results
-    nyaa_query = Nyaa.search('illo que pasa')
-
-    if len(nyaa_query) > 0:
-        for result in nyaa_query:
-            print(result['title'])
-    else:
-        print('Nothing here!')
-
-    # Nyaa.pantsu.cat results
-    pantsu_query = NyaaPantsu.search('new game')
-    if len(pantsu_query) > 0:
-        for result in pantsu_query:
-            print(result['title'])
-    else:
-        print('Nothing here!')
-
-### License
 
 MIT license.

requirements.txt

@@ -1,5 +1,2 @@
-certifi==2017.7.27.1
+requests==2.18.1
-chardet==3.0.4
+beautifulsoup4==4.6.0
-idna==2.5
-requests==2.18.3
-urllib3==1.22

setup.py

@@ -1,7 +1,7 @@
 from setuptools import setup, find_packages
 
 setup(name='nyaapy',
-      version='0.3.1',
+      version='0.4.1',
       url='https://github.com/juanjosalvador/nyaapy',
       download_url = 'https://github.com/juanjosalvador/nyaapy/archive/0.1.tar.gz',
       license='MIT',

src/nyaa.py

@@ -1,54 +0,0 @@
-import requests
-import xmltodict
-import json
-import collections
-
-class Nyaa:
-    '''
-     Makes a search query to nyaa.si with the given keyword that returns a
-     RSS file converted into a dictionary that we can use.
-    '''
-
-    def search(keyword):
-        nyaa_baseurl = "https://nyaa.si/?page=rss&c=1_0&f=0&q="
-
-        request  = requests.get(nyaa_baseurl + keyword)
-        response = xmltodict.parse(request.text)
-
-        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 = []
-
-        return results
-
-class NyaaPantsu:
-    '''
-     Makes a search query to nyaa.pantsu.cat with the given keyword that returns a
-     RSS file converted into a dictionary that we can use.
-    '''
-
-    def search(keyword):
-        nyaa_baseurl = "https://nyaa.pantsu.cat/feed?c=_&s=0&max=99999&userID=0&q="
-
-        request  = requests.get(nyaa_baseurl + keyword)
-        response = xmltodict.parse(request.text)
-
-        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 = []
-
-        return results

tests/test.py

@@ -1,20 +1,36 @@
-from NyaaPy.nyaa import Nyaa
+from NyaaPy import Nyaa, NyaaPantsu
-from NyaaPy.nyaa import NyaaPantsu
-import json
 
 # Nyaa.si results
-nyaa_query = Nyaa.search('koe no katachi 1080')
+def nyaa_search():
+    nyaa_query = Nyaa.search(keyword='koe no katachi 1080', category=1, subcategory=0, filters=0, page=0)
 
-if len(nyaa_query) > 0:
+    for nyaa in nyaa_query:
-    for result in nyaa_query:
+        print(nyaa)
-        print(result['title'])
+
-else:
+def nyaa_news():
-    print('Nothing here!')
+    news = Nyaa.news(number_of_results=5)
+    for n in news:
+        print(n)
 
 # Nyaa.pantsu.cat results
-pantsu_query = NyaaPantsu.search('new game!!')
+def pantsu_search():
-if len(pantsu_query) > 0:
+    pantsu_query = NyaaPantsu.search('new game!!')
-    for result in pantsu_query:
+    if len(pantsu_query) > 0:
+        for result in pantsu_query:
+            print(result['title'])
+    else:
+        print('Nothing here!')
+
+
+def pantsu_news():
+    news = NyaaPantsu.news(5)
+
+    for result in news:
         print(result['title'])
-else:
+
-    print('Nothing here!')
+# Uncomment whatever you want to test
+
+#nyaa_search()
+#pantsu_search()
+nyaa_news()
+#pantsu_news()