Created
April 14, 2020 14:23
-
-
Save Denniskamau/dbdede277fb30bbf91ba3841ccebea35 to your computer and use it in GitHub Desktop.
start scrapping method
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
... | |
def startScrapping(self,items,book_data): | |
#Get the current working directory | |
current_directory = os.getcwd() | |
# Create a folder named books to store the srapped images | |
path = os.path.join(current_directory,r"books") | |
self.createDirectory(path) | |
counter = 1 | |
#Loop through the product list | |
for book in book_data: | |
try: | |
product = book.find('div',class_="product") | |
url = product.find('a') | |
full_url = url.get('href') | |
page=urllib.request.urlopen('https://textbookcentre.com'+full_url) | |
soup = BeautifulSoup(page, 'html.parser') | |
data = soup.find('article',class_='product_page') | |
image = data.find('div',id='product-images') | |
image = image.find('a') | |
image_url = image.get('href') | |
#Get the title of the book so as the save each book with its title | |
title_data = data.find('div',class_='col-sm-6 product_main') | |
title = title_data.find('h1') | |
fullpath = os.path.join(path,title.text) | |
#Save the book | |
urllib.request.urlretrieve('https://textbookcentre.com'+image_url, " {}/{}.jpg".format(path,title.text)) | |
if counter == items: | |
print('INFO: finished') | |
return counter | |
else: | |
print('INFO: saved {} {}'.format(title.text,counter)) | |
counter +=1 | |
except Exception as e: | |
print('ERROR:',e) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment