From 5e454087f052393d3e20ec4ff13aeda3e9eaa1bb Mon Sep 17 00:00:00 2001
From: Ankit Kaurav <53783410+kauravankit25@users.noreply.github.com>
Date: Tue, 18 Aug 2020 23:57:25 +0530
Subject: [PATCH] Add files via upload

---
 .../flipkart_product_reviews/flipkart.py      | 84 +++++++++++++++++++
 .../flipkart_product_reviews/readme.md.txt    |  1 +
 2 files changed, 85 insertions(+)
 create mode 100644 Web-Scraping/flipkart_product_reviews/flipkart.py
 create mode 100644 Web-Scraping/flipkart_product_reviews/readme.md.txt

diff --git a/Web-Scraping/flipkart_product_reviews/flipkart.py b/Web-Scraping/flipkart_product_reviews/flipkart.py
new file mode 100644
index 00000000..94387f99
--- /dev/null
+++ b/Web-Scraping/flipkart_product_reviews/flipkart.py
@@ -0,0 +1,84 @@
+from bs4 import BeautifulSoup
+
+import requests
+
+URL = input("ENTER PRODUCT URL: ")
+
+
+req_data = requests.get(URL)
+review_soup = BeautifulSoup(req_data.content, "html.parser")
+
+base_url = "https://www.flipkart.com"
+data = review_soup.find('div', {"class": "swINJg _3nrCtb"}).find_parent().get("href")
+
+review_url = base_url + data
+all_review_data = requests.get(review_url)
+all_review_soup = BeautifulSoup(all_review_data.content, "html.parser")
+review_url
+
+all_reviews = review_soup.find_all('div', {'class': 'col _39LH-M'})
+len(all_reviews)
+
+header_list = []
+detailed_review_list = []
+user_list = []
+rating_list = []
+like_dislikes_list = []
+count = 0
+base_url = "https://www.flipkart.com"
+
+while(count<11):
+    
+    print(review_url)
+    all_review_data = requests.get(review_url)
+    all_review_soup = BeautifulSoup(all_review_data.content, "html.parser")
+    all_reviews = all_review_soup.find_all('div', {'class': 'ooJZfD _2oZ8XT col-9-12'})
+    #print(all_reviews)   
+    for review in all_reviews:
+        header = review.find_all("p", {"class": "_2xg6Ul"})
+        user = review.find_all("p", {"class": "_3LYOAd _3sxSiS"})
+        detailed_review = review.find_all("div", {"class": "qwjRop"})
+        rating = review.find_all("div", {"class": "hGSR34 E_uFuv"})
+        likes_dislikes = review.find_all("span", {"class": "_1_BQL8"})
+
+        header = [e.text for e in header]
+        user = [e.text for e in user]
+        detailed_review = [e.text for e in detailed_review]
+        rating = [e.text for e in rating]
+        likes_dislikes = [e.text for e in likes_dislikes]
+
+        header_list.append(header)
+        user_list.append(user)
+        detailed_review_list.append(detailed_review)
+        rating_list.append(rating)
+        like_dislikes_list.append(likes_dislikes)
+
+    count+=1
+    review_url = base_url + all_review_soup.find_all("a", {"class": "_3fVaIS"})[-1].get("href")
+
+
+user_list
+
+base_url = "https://www.flipkart.com"
+data = review_soup.find('div', {"class": "swINJg _3nrCtb"}).find_parent().get("href")
+
+review_url = base_url + data
+review_url
+
+
+
+user_list = [item for sublist in user_list for item in sublist]
+header_list = [item for sublist in header_list for item in sublist]
+detailed_review_list = [item for sublist in detailed_review_list for item in sublist]
+rating_list = [item for sublist in rating_list for item in sublist]
+like_dislikes_list = [item for sublist in like_dislikes_list for item in sublist]
+
+i=0
+while(i<20):
+    print(str(i+1) + ". " + user_list[i] + ":")
+    print(rating_list[i] + " stars")
+    print(header_list[i])
+    print(detailed_review_list[i])
+    print(like_dislikes_list[i])
+    print("\n\n")
+    i+=1
diff --git a/Web-Scraping/flipkart_product_reviews/readme.md.txt b/Web-Scraping/flipkart_product_reviews/readme.md.txt
new file mode 100644
index 00000000..93083c22
--- /dev/null
+++ b/Web-Scraping/flipkart_product_reviews/readme.md.txt
@@ -0,0 +1 @@
+Asks the user for the URL of the product they are interested in and then scrapes 10 pages of reviews for them.
\ No newline at end of file