feat: Search engine UI added (#3)

* feat: initial commit

* chore: cleanup

* chore: reorg

* feat: final and cleanup

* chore: final touchups

* feat: added build script

* style: style fix

* feat: updated readme and moved to src

* feat: search engine added

* feat: finsihed search Engine

* chore: search engine Done

.gitignore

@@ -164,3 +164,5 @@ cython_debug/
 logs.txt
 index.json
 indexed.json
+titles.json
+.archive

README.md

@@ -1,2 +1,20 @@
-# Phantom
-Distributed Crawler Indexing Engine
+# Phantom Search
+Light weight python based search engine
+
+## Set-up
+1) open `crawl.sh` and update the parameters
+
+```shell
+python phantom.py --num_threads 8 --urls "site1.com" "site2.com"
+```
+2) now run crawl.sh by typing 
+```shell
+./crawl.sh
+```
+This crawls the web and saves indices into `index.json` file
+
+3) run `build.sh` to Process the indices and run the `Query Engine`
+
+4) now everytime you can start the query engine by running the file `query_engine.py`
+
+

build.sh

@@ -0,0 +1,9 @@
+source .env/bin/activate
+
+pip install -r requirements.txt
+clear
+echo "Installation done"
+python3 -m src.phantom_indexing
+echo "Phantom Processing done"
+clear
+python3 -m src.query_engine

crawl.sh

@@ -1,6 +1,5 @@
 python3 -m venv .env
 source .env/bin/activate
 
-cd phantom_crawler
 pip install -r requirements.txt
-python3 phantom_engine.py
+python3 -m src.phantom --num_threads 10 --urls "https://www.geeksforgeeks.org/" "https://stackoverflow.com/questions" --show_logs True --print_logs True --sleep 60

phantom.py

@@ -0,0 +1,26 @@
+from flask import Flask, render_template, request
+from src.query_engine import Phantom_Query
+from src.phantom_engine import Parser
+
+app = Flask(__name__)
+engine = Phantom_Query("src/indexed.json", titles="src/titles.json")
+parser = Parser()
+
+@app.route('/', methods=['GET', 'POST'])
+def home():
+    input_text = ""
+    if request.method == 'POST':
+        input_text = request.form.get('input_text')
+        result = process_input(input_text)
+        return render_template('result.html', result=result, input_text=input_text)
+    return render_template('home.html', input_text=input_text)
+
+def process_input(input_text):
+    result = engine.query(input_text, count=20)
+    #(doc, score, title)
+    print("results ; \n\n")
+    print(result)
+    return result
+
+if __name__ == '__main__':
+    app.run()