Shreya

.gitignore

@@ -127,3 +127,7 @@ dmypy.json
 
 # Pyre type checker
 .pyre/
+
+
+*.csv
+user_data.json

README.md

@@ -183,11 +183,11 @@ python slash.py --search "philips hue" --num 5
 
 <table>
   <tr>
-    <td align="center"><a href="http://www.shubhammankar.com/"><img src="https://avatars.githubusercontent.com/u/29366125?v=4" width="75px;" alt=""/><br /><sub><b>Shubham Mankar</b></sub></a></td>
-    <td align="center"><a href="https://github.com/pratikdevnani"><img src="https://avatars.githubusercontent.com/u/43350493?v=4" width="75px;" alt=""/><br /><sub><b>Pratik Devnani</b></sub></a><br /></td>
-    <td align="center"><a href="https://github.com/moksh98"><img src="https://avatars.githubusercontent.com/u/29693765?v=4" width="75px;" alt=""/><br /><sub><b>Moksh Jain</b></sub></a><br /></td>
-    <td align="center"><a href="https://rahilsarvaiya.tech/"><img src="https://avatars0.githubusercontent.com/u/32304956?v=4" width="75px;" alt=""/><br /><sub><b>Rahil Sarvaiya</b></sub></a><br /></td>
-    <td align="center"><a href="https://github.com/annie0467"><img src="https://avatars.githubusercontent.com/u/17164255?v=4" width="75px;" alt=""/><br /><sub><b>Anushi Keswani</b></sub></a><br /></td>
+    <td align="center"><a href="https://github.com/antgad"><img src="https://avatars.githubusercontent.com/u/37169203?v=4" width="75px;" alt=""/><br /><sub><b>Anant Gadodia</b></sub></a></td>
+    <td align="center"><a href="https://github.com/AnmolikaGoyal"><img src="https://avatars.githubusercontent.com/u/68813421?v=4" width="75px;" alt=""/><br /><sub><b>Anmolika Goyal</b></sub></a><br /></td>
+    <td align="center"><a href="https://github.com/shubhangij12"><img src="https://avatars.githubusercontent.com/u/48826459?v=4" width="75px;" alt=""/><br /><sub><b>Shubhangi Jain</b></sub></a><br /></td>
+    <td align="center"><a href="https://github.com/shreyakarra"><img src="https://avatars0.githubusercontent.com/u/89954066?v=4" width="75px;" alt=""/><br /><sub><b>Shreya Karra</b></sub></a><br /></td>
+    <td align="center"><a href="https://github.com/srujanarao"><img src="https://avatars.githubusercontent.com/u/6882921?v=4" width="75px;" alt=""/><br /><sub><b>Srujana Rao</b></sub></a><br /></td>
   </tr>
 </table>
 

requirements.txt

@@ -34,4 +34,6 @@ urllib3==1.26.6
 Werkzeug==1.0.1
 wheel==0.37.0
 zipp==3.5.0
-DateTime==4.3
+DateTime==4.3
+lxml==4.6.3
+requests-oauthlib==1.3.0

src/csv_writer.py

@@ -0,0 +1,19 @@
+import csv
+from datetime import datetime
+import os
+
+
+def write_csv(arr,product,file_path):
+	''' Returns the CSV file with the naming nomenclature as 'ProductDate_Time'
+        Parameters- product: product entered by the user, file_path: path where the csv needs to be stored
+        Returns- file_name: CSV file '''
+	os.chdir(file_path)
+	keys = arr[0].keys()
+	now=datetime.now()
+	file_name=product+now.strftime("%m%d%y_%H%M")+'.csv'
+	a_file = open(file_name, "w", newline='')
+	dict_writer = csv.DictWriter(a_file, keys)
+	dict_writer.writeheader()
+	dict_writer.writerows(arr)
+	a_file.close()
+	return file_name

src/formatter.py

@@ -15,25 +15,36 @@
 from datetime import datetime
 import math
 
-def formatResult(website, titles, prices, links):
+def formatResult(website, titles, prices, links,ratings,df_flag, currency):
     """
     The formatResult function takes the scraped HTML as input, and extracts the 
     necessary values from the HTML code. Ex. extracting a price '$19.99' from
     a paragraph tag.
     """
-    title, price, link = '', '', ''
+
+    title, price, link, rating, converted_cur = '', '', '', '', ''
     if titles: title = titles[0].get_text().strip()
     if prices: price = prices[0].get_text().strip()
+    if '$' not in price:
+        price='$'+price
     if links: link = links[0]['href']
+    if ratings: rating = ratings[0].get_text().strip().split()[0]
+    if df_flag==0: title=formatTitle(title)
+    if df_flag==0: link=formatTitle(link)
+    if currency: converted_cur = getCurrency(currency, price)
     product = {
         'timestamp': datetime.now().strftime("%d/%m/%Y %H:%M:%S"),
-        "title": formatTitle(title),
+        "title": title,
         "price": price, 
-        # "link":f'www.{website}.com{link}', 
+        "link":f'www.{website}.com{link}', 
         "website": website,
+        "rating" : rating,
+        "converted price": converted_cur
     }
+
     return product
 
+
 def sortList(arr, sortBy, reverse):
     """
     The sortList function is used to sort the products list based on the
@@ -43,7 +54,7 @@ def sortList(arr, sortBy, reverse):
         return sorted(arr, key=lambda x: getNumbers(x["price"]), reverse=reverse)
     # To-do: sort by rating
     elif sortBy == "ra":
-        # return sorted(arr, key=lambda x: getNumbers(x.price), reverse=reverse)
+        return sorted(arr, key=lambda x: getNumbers(x["rating"]), reverse=reverse)
         pass
     return arr
 
@@ -62,6 +73,7 @@ def formatTitle(title):
         return title[:40] + "..."
     return title
 
+
 def getNumbers(st):
     """
     The getNumbers function extracts float values (price) from a string.
@@ -75,4 +87,15 @@ def getNumbers(st):
         ans = float(ans)
     except:
         ans = math.inf
-    return ans
+    return ans
+
+def getCurrency(currency, price):
+
+    converted_cur = 0.0
+    if len(price)>1 :
+        if currency == "inr":
+            converted_cur = 75 * int(price[(price.index("$")+1):price.index(".")].replace(",",""))
+        elif currency == "euro":
+            converted_cur = 1.16 * int(price[(price.index("$")+1):price.index(".")].replace(",",""))
+        converted_cur=currency.upper()+' '+str(converted_cur)
+    return converted_cur

src/full_version.py

@@ -0,0 +1,105 @@
+import json
+import os
+import pandas as pd
+import scraper
+
+class full_version:
+	def __init__(self):
+		self.data={}
+		self.name=""
+		self.email=""
+		self.user_data = os.path.join(
+			os.path.dirname(
+				os.path.dirname(
+					os.path.abspath(__file__))),
+			"json", 
+			"user_data.json"
+			)
+		self.user_list = os.path.join(
+			os.path.dirname(
+				os.path.dirname(
+					os.path.abspath(__file__))),
+			"csvs", 
+			"user_list.csv"
+			)
+		self.df=pd.DataFrame()
+		pd.set_option('display.max_rows', None)
+		pd.set_option('display.max_columns', None)
+		pd.set_option('display.width', None)
+		pd.set_option('display.max_colwidth', 40)
+
+
+	def login(self):
+		if not os.path.exists(self.user_data):
+			print("Welcome to Slash!")
+			print("Please enter the following information: ")
+			name=input("Name: ")
+			email=input("Email: ")
+			self.data['name']=name
+			self.data['email']=email
+			with open(self.user_data, 'w') as outfile:
+				json.dump(self.data, outfile)
+			self.name=name
+			self.email=email
+		else:
+			with open(self.user_data) as json_file:
+				data = json.load(json_file)
+				self.name=data['name']
+				self.email=data['email']
+		return self.name, self.email
+
+	def search_fn(self):
+		prod=input("Enter name of product to Search: ")
+		self.scrape(prod)
+		ch=int(input("\n\nEnter 1 to save product to list \nelse enter any other key to continue"))
+		if ch==1:
+			indx=int(input("Enter row number of product to save: "))
+			if indx<len(self.df):
+				if os.path.exists(self.user_list):
+					old_data=pd.read_csv(self.user_list)
+				else:
+					old_data=pd.DataFrame()
+				if self.df.title[indx] not in old_data:
+					old_data=pd.concat([old_data,self.df.iloc[[indx]]])
+					print(self.df.iloc[[indx]])
+				old_data.to_csv(self.user_list, index=False,header=self.df.columns)
+
+		pass
+
+	def extract_list(self):
+		if os.path.exists(self.user_list):
+			old_data=pd.read_csv(self.user_list)
+			print(old_data)
+		else:
+			print("No saved data found.")
+		pass
+
+	def scrape(self,prod):
+		products_1 = scraper.searchAmazon(prod,1)
+		products_2 = scraper.searchWalmart(prod,1)
+		products_3 = scraper.searchEtsy(prod,1)
+		results=scraper.driver(prod,df_flag=1)
+		#esults = formatter.sortList(results, "ra" , True)
+		self.df=pd.DataFrame.from_dict(results, orient='columns')
+		print(self.df)
+
+
+
+	def driver(self):
+		self.login()
+		flag_loop=1
+		print("Welcome ",self.name)
+		while flag_loop==1:
+			print("Select from following:")
+			print("1. Search new product\n2. See exiting list\n3. Exit")
+			choice=int(input())
+			if choice==1:
+				self.search_fn()
+			elif choice==2:
+				self.extract_list()
+			elif choice==3:
+				print("Thank You for Using Slash")
+				flag_loop = 0
+			else:
+				print("Incorrect Option")
+