Added support to download subtitle => automatically

README.md

@@ -17,6 +17,10 @@ python setup.py install
 python search.py
 ```
 
+---
+### What's new
+Added support to download subtitles for the movie as well
+
 ---
 ### What's next
 - Allow user to stop movie search in between

setup.py

@@ -6,7 +6,7 @@
 setup(
     name='search-torrent',
     description='Search for torrents using command line',
-    version='1.1.4',
+    version='1.2.0',
     url='http://github.com/rajat19/torrent-crawler',
     download_url='https://github.com/rajat19/torrent-crawler/releases',
     author='Rajat Srivastava',

torrent_crawler/constants.py

@@ -7,6 +7,11 @@ class Constants:
     order_by = ['rating', 'seeds', 'peers', 'year', 'likes', 'alphabetical', 'downloads']
     search_url = 'https://yts.am/browse-movies/{0}/{1}/{2}/{3}/{4}'
 
+    # subtitle search constants
+    subtitle_base_url = 'http://www.yifysubtitles.com/{0}'
+    subtitle_search_url = 'http://www.yifysubtitles.com/search?q={0}'
+    subtitle_movie_url = 'http://www.yifysubtitles.com/movie-imdb/{0}'
+
     # texts
     search_string_text = 'Please enter search string: '
     genre_selection_text = 'Do you want to search some specific genre: '
@@ -21,6 +26,10 @@ class Constants:
     click_link_text = 'Torrent link will open automatically, If not then Click this link: '
     restart_search_text = 'Do you want to start searching again'
     thanks_text = 'Thanks for using torrent-search . Keep Seeding'
+    subtitles_selection_text = 'Do you want to download subtitles for this movie'
+    subtitle_language_text = 'Select language to get subtitles: '
+    download_zip_text = 'Subtitle would be downloaded in {0}{1}. Please check there.'
+    another_movies_text = 'Do you want to download another {0}{1} movie'
 
     # note
     specific_genre_note = 'Movies would be crawled for only {0} genre'

torrent_crawler/crawler.py

@@ -4,7 +4,7 @@
 import os
 import re
 import requests
-from torrent_crawler.progress_bar import ProgressBar
+from torrent_crawler.helper import update_progress
 
 
 class Crawler:
@@ -119,7 +119,7 @@ def crawl_list(self, crawl_url):
                     print('{}: {}'.format(current_movie_count, movie_name))
                 if self.should_save_list:
                     self.save_list(movie)
-                ProgressBar.update_progress(current_movie_count, movies_count)
+                update_progress(current_movie_count, movies_count)
                 current_movie_count += 1
             page_no += 1
         return movies
@@ -150,6 +150,10 @@ def crawl_movie(self, movie_link, movie_details):
             movie_details['ratings'] = rating_list
         elif self.should_print_to_console:
             print("{} got no info, not saving it".format(movie_details['name']))
+        movie_tech_specs = soup.find('div', {'id': 'movie-tech-specs'})
+        if movie_tech_specs:
+            tech_spec = movie_tech_specs.find('div', {'class': 'tech-spec-info'})
+            movie_details['subtitle_url'] = tech_spec.find('a').get('href')
         return movie_details
 
 

torrent_crawler/search.py

@@ -1,22 +1,9 @@
-import os
-import sys
-import subprocess
 import traceback
 from torrent_crawler.constants import Constants
 from torrent_crawler.color import Color
 from torrent_crawler.crawler import Crawler
-
-
-def print_long_hash():
-    print('##########################################')
-
-
-def print_wrong_option():
-    print(Constants.wrong_option_text)
-
-
-def get_yes_no():
-    return '{0}\n{1}\n'.format(Color.get_colored_yes(), Color.get_colored_no())
+from torrent_crawler.helper import open_magnet_link, print_wrong_option, get_yes_no, print_long_hash
+from torrent_crawler.subtitle import Subtitle
 
 
 class SearchQuery:
@@ -32,16 +19,6 @@ class Search:
     def __init__(self, search_query: SearchQuery):
         self.search_query = search_query
 
-    def open_magnet(self, magnet):
-        if sys.platform.startswith('win32') or sys.platform.startswith('cygwin'):
-            os.startfile(magnet)
-        elif sys.platform.startswith('darwin'):
-            subprocess.Popen(['open', magnet],
-                             stdout=subprocess.PIPE, stderr=subprocess.PIPE)
-        else:
-            subprocess.Popen(['xdg-open', magnet],
-                             stdout=subprocess.PIPE, stderr=subprocess.PIPE)
-
     def get_available_torrents(self, movie_selected):
         if self.search_query.quality == 'all':
             return movie_selected['torrents']
@@ -76,7 +53,7 @@ def show_movies(self, movies):
         if len(available_torrents.values()) == 0:
             print('{0}{1}{2}'.format(Color.RED, Constants.no_torrent_text, Color.END))
         else:
-            ati=1
+            ati = 1
             for torrent_format in available_torrents:
                 print('{0}{1}: {2}{3}'.format(Color.YELLOW, ati, torrent_format, Color.END))
                 ati += 1
@@ -90,11 +67,18 @@ def show_movies(self, movies):
                 Color.print_bold_string(Constants.movie_quality_text)
                 qu = int(input())
                 torrent_link = list(available_torrents.values())[qu - 1]
-                self.open_magnet(torrent_link)
+                open_magnet_link(torrent_link)
                 Color.print_bold_string('{0}{1}{2}{3}'.format(
                     Constants.click_link_text, Color.RED, torrent_link, Color.END))
             print_long_hash()
-            print('Want to download another {0}{1} movie'.format(
+            Color.print_bold_string(Constants.subtitles_selection_text)
+            download_subtitle = input(get_yes_no())
+            if download_subtitle == 'y' or download_subtitle == 'Y':
+                subtitle = Subtitle()
+                subtitle.search_subtitle(movie_selected['subtitle_url'])
+
+            print_long_hash()
+            print(Constants.another_movies_text.format(
                 Color.RED, Color.get_bold_string(self.search_query.search_term)))
             reshow_movies = input(get_yes_no())
             if reshow_movies == 'y' or reshow_movies == 'Y':
@@ -135,10 +119,10 @@ def take_genre_input():
             while True:
                 g = int(input())
                 if 1 <= g <= 27:
+                    break
+                else:
                     print_wrong_option()
                     continue
-                else:
-                    break
             Color.print_colored_note(Constants.specific_genre_note.format(genre_options[g]))
         else:
             Color.print_colored_note(Constants.all_genre_note)

torrent_crawler/subtitle.py

@@ -0,0 +1,76 @@
+from bs4 import BeautifulSoup
+import requests
+from torrent_crawler.color import Color
+from torrent_crawler.constants import Constants
+from torrent_crawler.helper import download_srt, print_wrong_option
+
+
+class Subtitle:
+    @staticmethod
+    def get_search_url(search_term, page_no):
+        q = search_term
+        if page_no > 2:
+            q += page_no
+        return Constants.subtitle_search_url.format(q)
+
+    def crawl_list(self, search_term):
+        page_no = 1
+        has_next_page = True
+        while has_next_page:
+            url = self.get_search_url(search_term, page_no)
+            req = requests.get(url)
+            soup = BeautifulSoup(req.text, features='html5lib')
+            media_list = soup.find_all('li', {'class': 'media-movie-clickable'})
+            for media in media_list:
+                media_body = media.find('div', {'class': 'media-body'})
+                media_link = media_body.find('a').get('href')
+                media_name = media.find('h3', {'class': 'media-heading'}).text
+
+    @staticmethod
+    def crawl_movie(url):
+        req = requests.get(url)
+        soup = BeautifulSoup(req.text, features='html5lib')
+        subtitle_table = soup.find('table', {'class': 'other-subs'}).find('tbody').find_all('tr')
+        subtitles = {}
+        subtitle_languages = []
+        for subtitle in subtitle_table:
+            rating = subtitle.find('td', {'class': 'rating-cell'}).text
+            language = subtitle.find('td', {'class': 'flag-cell'})\
+                .find('span', {'class': 'sub-lang'}).text
+            download_link = subtitle.find('a').get('href').replace('/subtitles/', 'subtitle/')
+            link = Constants.subtitle_base_url.format(download_link + '.zip')
+            subtitle_languages.append(language)
+            if language not in subtitles:
+                subtitles[language] = []
+            subtitles[language].append({
+                'rating': rating,
+                'link': link
+            })
+        return subtitles
+
+    @staticmethod
+    def take_language_input(languages):
+        Color.print_bold_string(Constants.subtitle_language_text)
+        for i in range(len(languages)):
+            print('{0}{1}: {2}{3}'.format(Color.YELLOW, i+1, languages[i], Color.END))
+        while True:
+            lang = int(input())
+            if 1 <= lang <= len(languages):
+                break
+            else:
+                print_wrong_option()
+                continue
+        return languages[lang-1]
+
+    def search_subtitle(self, url):
+        # url = Constants.subtitle_movie_url.format(imdb_id)
+        subtitles = self.crawl_movie(url)
+        lang = self.take_language_input(list(subtitles.keys()))
+        # Download first subtitle for that language as it is highest rated
+        subtitle_link = subtitles[lang][0]['link']
+        download_srt(subtitle_link)
+
+
+if __name__ == '__main__':
+    s = Subtitle()
+    s.search_subtitle('tt4154756')