|
| 1 | +# HTML Page Read and Upload |
| 2 | +# Import useful libraries and classes. |
| 3 | + |
| 4 | +from urllib.request import urlopen as uReq |
| 5 | +from bs4 import BeautifulSoup as soup |
| 6 | + |
| 7 | +# html page upload and read in web_page variable. |
| 8 | +my_url= "https://www.flipkart.com/search?p%5B%5D=facets.brand%255B%255D%3DSamsung&sid=tyy%2F4io&sort=recency_desc&wid=1.productCard.PMU_V2_1" |
| 9 | +web_page= uReq(my_url) |
| 10 | +page_html= web_page.read() |
| 11 | + |
| 12 | +# Parsing |
| 13 | +# html parser. It is to beautify the HTML code. |
| 14 | +page_soup= soup(page_html) |
| 15 | + |
| 16 | +# Extraction of information |
| 17 | +# read class attribute from web page in containers variable. |
| 18 | +# Print the length of containers. |
| 19 | + |
| 20 | +containers= page_soup.findAll("div", {"class": "_2kHMtA"}) |
| 21 | +print(len(containers)) |
| 22 | + |
| 23 | +# Extracting Product Name |
| 24 | +# The product_name_list contains the name of product extracted using find function using div tag and |
| 25 | +# class name |
| 26 | + |
| 27 | +product_name_list = [] |
| 28 | + |
| 29 | +for box in containers: |
| 30 | + # name of product is extracted using div tag with class name as given in website |
| 31 | + product_name = box.find("div", class_="_4rR01T") |
| 32 | + # the extracted names is stored in a list |
| 33 | + product_name_list.append(product_name.string) |
| 34 | + |
| 35 | +# Extracting Ratings |
| 36 | +# The rating_list contains the ratings of product extracted using find function using div tag and class name |
| 37 | + |
| 38 | +rating_list = [] |
| 39 | + |
| 40 | +for box in containers: |
| 41 | + # rating of product is extracted using div tag with class name as given in website, if the rating is None, then 0.0 is used. |
| 42 | + rating = box.find("div", class_="_3LWZlK") |
| 43 | + if rating != None: |
| 44 | + rating_list.append(rating.text) |
| 45 | + else: |
| 46 | + rating_list.append('0.0') |
| 47 | +# Extracting Price of Product |
| 48 | +# The price_list contains the price of product extracted using find function using div tag and class name |
| 49 | +price_list = [] |
| 50 | + |
| 51 | +for box in containers: |
| 52 | + # price of product is extracted using div tag with class name as given in website |
| 53 | + price = box.find("div", class_="_30jeq3") |
| 54 | + # the extracted price is stored in a list after string Rupees sign. |
| 55 | + price_list.append(price.string.strip('₹')) |
| 56 | + |
| 57 | +# The container in website contains a list of information of the product which is |
| 58 | +# extracted using find function using li tag and class name |
| 59 | +# here n is length of containers in 1 page. |
| 60 | + |
| 61 | +n = len(containers) |
| 62 | + |
| 63 | +# list to store RAM of phones |
| 64 | +ram_list = [] |
| 65 | +# list to store ROM of phones |
| 66 | +rom_list = [] |
| 67 | +# list to store Display Screen of phones |
| 68 | +display_list = [] |
| 69 | +# list to store Camera Specification of phones |
| 70 | +camera_list = [] |
| 71 | +# list to store Battery Life of phones |
| 72 | +battery_life_list = [] |
| 73 | +# list to store Warranty Period of phones |
| 74 | +warranty_list = [] |
| 75 | +# temporary list to store the all the list of phones's specifications |
| 76 | +temp_list = [] |
| 77 | + |
| 78 | + |
| 79 | +for box in containers: |
| 80 | + # one list out of all product list is extracted using li tag with class name as given in website |
| 81 | + temp_box = box.findAll("li", class_="rgWa7D") |
| 82 | + temp_list.append(temp_box) |
| 83 | + |
| 84 | +for i in range(n): |
| 85 | + # this loop extracts the values stored in the list of one container. |
| 86 | + # since in the website the RAM & ROM of phoes are listed together |
| 87 | + # so it is stored in a list and then splitted as per given splittor element. |
| 88 | + split_list = temp_list[i][0].string.split('|') |
| 89 | + # the extracted RAM is stored in a list |
| 90 | + ram_list.append(split_list[0]) |
| 91 | + # the extracted ROM is stored in a list |
| 92 | + rom_list.append(split_list[1]) |
| 93 | + # the extracted display is stored in a list |
| 94 | + display_list.append(temp_list[i][1].string) |
| 95 | + # the extracted camera is stored in a list |
| 96 | + camera_list.append(temp_list[i][2].string) |
| 97 | + # the extracted battery is stored in a list |
| 98 | + battery_life_list.append(temp_list[i][3].string) |
| 99 | + # the extracted warranty is stored in a list |
| 100 | + warranty_list.append(temp_list[i][-1].string) |
| 101 | + |
| 102 | +# Creating Pandas DataFrame from Data scraped from Web |
| 103 | +# Importing Pandas to create a DataFrame |
| 104 | +import pandas as pd |
| 105 | +# Creating a Dictionary to store List values and creating DataFrame |
| 106 | +dictionary = {'Product_Name':product_name_list, 'Ratings':rating_list, 'Price':price_list, 'RAM_Storage':ram_list, |
| 107 | + 'ROM_Storage':rom_list, 'Display_Screen':display_list, 'Camera':camera_list, 'Battery_Life':battery_life_list, |
| 108 | + 'Warranty_Life':warranty_list} |
| 109 | +dataframe = pd.DataFrame(dictionary) |
| 110 | +# Head of DataFrame |
| 111 | +dataframe.head() |
| 112 | + |
| 113 | +# Tail of DataFrame |
| 114 | +dataframe.tail() |
0 commit comments