Mohammed Ouahman mohammedouahman
🇵🇸
mohammedouahman
/ scrape.py
Created
November 19, 2021 16:46
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| import pandas as pd | |
| import numpy as np | |
| import matplotlib.pyplot as plt | |
| import seaborn as sns | |
| %matplotlib inline | |
| import re | |
| import time | |
| from datetime import datetime | |
| import matplotlib.dates as mdates | |
| import matplotlib.ticker as ticker |
mohammedouahman
/ scrape.py
Created
November 19, 2021 16:51
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| no_pages = 2 | |
| def get_data(pageNo): | |
| headers = {"User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:66.0) Gecko/20100101 Firefox/66.0", "Accept-Encoding":"gzip, deflate", "Accept":"text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8", "DNT":"1","Connection":"close", "Upgrade-Insecure-Requests":"1"} | |
| r = requests.get('https://www.amazon.in/gp/bestsellers/books/ref=zg_bs_pg_'+str(pageNo)+'?ie=UTF8&pg='+str(pageNo), headers=headers)#, proxies=proxies) | |
| content = r.content | |
| soup = BeautifulSoup(content) | |
| #print(soup) |
mohammedouahman
/ scrape.py
Created
November 19, 2021 16:51
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| results = [] | |
| for i in range(1, no_pages+1): | |
| results.append(get_data(i)) | |
| flatten = lambda l: [item for sublist in l for item in sublist] | |
| df = pd.DataFrame(flatten(results),columns=['Book Name','Author','Rating','Customers_Rated', 'Price']) | |
| df.to_csv('amazon_products.csv', index=False, encoding='utf-8') |
mohammedouahman
/ scrape.py
Created
November 19, 2021 16:53
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| df = pd.read_csv("amazon_products.csv") | |
| df.shape |
mohammedouahman
/ gist:96547d6ba2b58cbfa5be6336da46296c
Created
November 19, 2021 16:54
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| df.head(61) |
mohammedouahman
/ scrape.py
Created
November 19, 2021 17:02
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Book Name Author Rating Customers_Rated Price | |
| 0 The Power of your Subconscious Mind Joseph Murphy 4.5 out of 5 stars 13,948 ₹ 99.00 | |
| 1 Think and Grow Rich Napoleon Hill 4.5 out of 5 stars 16,670 ₹ 99.00 | |
| 2 Word Power Made Easy Norman Lewis 4.4 out of 5 stars 10,708 ₹ 130.00 | |
| 3 Mathematics for Class 12 (Set of 2 Vol.) Exami... R.D. Sharma 4.5 out of 5 stars 18 ₹ 930.00 | |
| 4 The Girl in Room 105 Chetan Bhagat 4.3 out of 5 stars 5,162 ₹ 149.00 | |
| ... ... ... ... ... ... | |
| 56 COMBO PACK OF Guide To JAIIB Legal Aspects Pri... MEC MILLAN 4.5 out of 5 stars 114 ₹ 1,400.00 | |
| 57 Wren & Martin High School English Grammar and ... Rao N 4.4 out of 5 stars 1,613 ₹ 400.00 | |
| 58 Objective General Knowledge Sanjiv Kumar 4.2 out of 5 stars 742 ₹ 254.00 |
OlderNewer