Added-Movie-Info-Telegram-Bot in Python (HarshCasper#835)

* Added-Movie-Info-Telegram-Bot in Python

* Added movie-info-bot in python

Fixes HarshCasper#832

* Updated bot.py

* Formatted code

Python/Movie-Info-Telegram-Bot/.env.example

@@ -0,0 +1 @@
+API_KEY = "xxxxxxxxxxxxxxxxxxx"

Python/Movie-Info-Telegram-Bot/README.md

@@ -0,0 +1,43 @@
+# Movie Info Telegram Bot
+
+## Description
+A telegram Bot made using python which scrapes IMDb website and has the following functionalities
+1. Replies to a movie name with genre and rating of the movie
+2. Replies to a genre with a list of top movies and tv shows belonging to that genre
+
+## Setup Instructions
+
+1. Install required packages:
+
+       pip install -r requirements.txt
+
+2. Create a bot in telegram:
+
+       1. Go to @BotFather and click /start and type /newbot and give it a name. 
+       2. Choose a username and get the token 
+3. Paste the token in a .env file (Take [.env.example](.env.example) as an example) 
+
+4. Run the python script to start the bot
+
+5. Type /start command to start conversation with the chatbot.
+
+6. Type /name <movie_name> to get the genre and Rating of the movie. The bot replies with atmost three results.
+7. Type /genre \<genre> to get a list of movies and TV shows belonging to that genres
+
+## Output
+
+### /start command
+
+<img src="https://i.ibb.co/jwpJHKX/start.png">
+
+### /name command
+
+<img src="https://i.ibb.co/FzrGjSQ/movie.png">
+
+### /genre command
+
+<img src="https://i.ibb.co/VJQy108/genre.png">
+
+## Author
+
+[Aishwarya A J](https://github.com/aish2002)

Python/Movie-Info-Telegram-Bot/bot.py

@@ -0,0 +1,166 @@
+import logging
+import requests
+import re
+import urllib.request
+import urllib.parse
+import urllib.error
+from bs4 import BeautifulSoup
+import ssl
+import itertools
+from telegram.ext import Updater, CommandHandler, MessageHandler, Filters
+import decouple
+
+# Enable logging
+logging.basicConfig(format='%(asctime)s - %(name)s - %(levelname)s - %(message)s',
+                    level=logging.INFO)
+
+logger = logging.getLogger(__name__)
+
+TOKEN = decouple.config("API_KEY")
+
+# Define a few command handlers. These usually take the two arguments update and
+# context. Error handlers also receive the raised TelegramError object in error.
+
+
+def start(update, context):
+    """Send a message when the command /start is issued."""
+    update.message.reply_text(
+        'What can this bot do?\n\nThis bot gives brief information about any movie from IMDb website'
+        + '\nSend /name movie_name to know the genre and rating of the movie.\nSend /genre genre_name to'
+        + 'get the list of movies belonging to that genre'
+    )
+
+
+def help(update, context):
+    """Send a message when the command /help is issued."""
+    update.message.reply_text('Help!')
+
+
+def genre(update, context):
+    """Send a list of movies when the command /genre is issued."""
+    url = 'https://www.imdb.com/search/title/'
+    genre = str(update.message.text)[7:]
+    print(genre)
+    r = requests.get(url+'?genres='+genre)
+    soup = BeautifulSoup(r.text, "html.parser")
+    title = soup.find('title')
+    if title.string == 'IMDb: Advanced Title Search - IMDb':
+        update.message.reply_text("Sorry,No such genre.Try again")
+    else:
+        res = []
+        res.append(title.string+'\n')
+        tags = soup('a')
+        for tag in tags:
+            movie = re.search('<a href=\"/title/.*>(.*?)</a>', str(tag))
+            try:
+                if "&amp;" in movie.group(1):
+                    movie.group(1).replace("&amp;", "&")
+                res.append(movie.group(1))
+            except:
+                pass
+        stri = ""
+        for i in res:
+            stri += i+'\n'
+        update.message.reply_text(stri)
+
+
+def name(update, context):
+    """Send the first 3 search results of the movie name in IMDb site when the command /name is issued."""
+    movie = str(update.message.text)[6:]
+    print(movie)
+    res = get_info(movie)
+    stri = ""
+    for i in res:
+        for a in i:
+            stri += a+'\n'
+        stri += '\n'
+    update.message.reply_text(stri)
+
+
+def error(update, context):
+    """Log Errors caused by Updates."""
+    logger.warning('Update "%s" caused error "%s"', update, context.error)
+
+
+def get_info(movie):
+    "To scrape IMDb and get genre and rating of the movie "
+    url = 'https://www.imdb.com/find?q='
+    r = requests.get(url+movie+'&ref_=nv_sr_sm')
+    soup = BeautifulSoup(r.text, "html.parser")
+    title = soup.find('title')
+    tags = soup('a')
+    pre_url = ""
+    count = 0
+    lis = []
+    res = []
+    for tag in tags:
+        if(count > 2):
+            break
+        m = re.search('<a href=.*>(.*?)</a>', str(tag))
+        try:
+            lis = []
+            link = re.search('/title/(.*?)/', str(m))
+            new_url = 'https://www.imdb.com'+str(link.group(0))
+            if new_url != pre_url:
+                html = requests.get(new_url)
+                soup_each_title = BeautifulSoup(html.text, "html.parser")
+                movie_title = soup_each_title.find(
+                    'title').string.replace('- IMDb', ' ')
+                anchor = soup_each_title('a')
+                genre_string = "Genre : "
+                for each in anchor:
+                    genre = re.search(
+                        '<a href=\"/search/title\?genres=.*> (.*?)</a>', str(each))
+                    try:
+                        genre_string += genre.group(1)+' '
+                    except:
+                        pass
+                strong_tag = soup_each_title('strong')
+                for i in strong_tag:
+                    rating = re.search('<strong title=\"(.*?) based', str(i))
+                    try:
+                        rating_string = "IMDb Rating : "+rating.group(1)
+                    except:
+                        pass
+                details = "For more details : "+new_url
+                lis.append(movie_title)
+                lis.append(genre_string)
+                lis.append(rating_string)
+                lis.append(details)
+                pre_url = new_url
+                count += 1
+                res.append(lis)
+        except:
+            pass
+    return res
+
+
+def main():
+    """Start the bot."""
+    # Create the Updater and pass it your bot's token.
+    # Make sure to set use_context=True to use the new context based callbacks
+    updater = Updater(TOKEN, use_context=True)
+
+    # Get the dispatcher to register handlers
+    dp = updater.dispatcher
+
+    # on different commands - reply in Telegram
+    dp.add_handler(CommandHandler("start", start))
+    dp.add_handler(CommandHandler("help", help))
+    dp.add_handler(CommandHandler("name", name))
+    dp.add_handler(CommandHandler("genre", genre))
+
+    # log all errors
+    dp.add_error_handler(error)
+
+    # Start the Bot
+    updater.start_polling()
+
+    # Run the bot until you press Ctrl-C or the process receives SIGINT,
+    # SIGTERM or SIGABRT. This should be used most of the time, since
+    # start_polling() is non-blocking and will stop the bot gracefully.
+    updater.idle()
+
+
+if __name__ == '__main__':
+    main()

Python/Movie-Info-Telegram-Bot/requirements.txt

@@ -0,0 +1,12 @@
+APScheduler==3.6.3
+beautifulsoup4==4.9.3
+certifi==2020.12.5
+python-dateutil==2.8.1
+python-decouple==3.4
+python-telegram-bot==13.1
+pytz==2020.4
+requests==2.25.1
+six==1.15.0
+soupsieve==2.1
+tornado==6.1
+urllib3==1.26.2