I’m just learning python. I want to improve myself with examples. sorry for my English. I’m in the process of learning a new language. 🙂
The program pulls data from an e-commerce site.
when I want to save it as a csv file, each new data overwrites the previous data. I tried several examples but it didn’t work.
Thanks for your help.
import requests
import gettext
from bs4 import BeautifulSoup
import pandas as pd
import openpyxl as xls
import xlsxwriter`
baseurl = "https://www.trendyol.com"
headers = {'User-Agent':
'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/51.0.2704.106 Safari/537.36 OPR/38.0.2220.41'
}
for x in range(1,62):
r = requests.get(f'https://www.trendyol.com/cep-telefonu-x-c103498?pi={x}', headers=headers)
soup = BeautifulSoup(r.content, 'lxml')
productlist = soup.find_all('div', class_='p-card-wrppr')
for item in productlist:
productname = item.find('span', class_='prdct-desc-cntnr-name').getText()
productprice_old = item.find('div', class_='prc-box-sllng').getText()
productprice_discount = item.find('div', class_='prc-box-dscntd')
for productlink in item.find_all('a'):
productlink = baseurl+productlink.get('href')
if productprice_discount == None:
productprice_discount = productprice_old
else:
productprice_discount = productprice_discount.getText()
for merchant_name in productlink:
r = requests.get(productlink, headers=headers)
soup = BeautifulSoup(r.content, 'lxml')
merchant_name = soup.find('a', class_='merchant-text')
if merchant_name == None:
merchant_name = soup.find('a', class_='title')
if merchant_name == None:
merchant_name = soup.find('span', class_='product-description-market-place')
if merchant_name == None:
merchant_name = ('NULL')
else:
merchant_name = merchant_name.getText()
break
for product_image in productlink:
r = requests.get(productlink, headers=headers)
soup = BeautifulSoup(r.content, 'lxml')
product_image = soup.find_all('img', attrs={'class':'detail-section-img'})
image_src = [x['src'] for x in product_image]
image_src = [x for x in image_src if x.endswith('.jpg' or '.png')]
break
data = [ [productname,productlink,productprice_old,productprice_discount,merchant_name,image_src] ]
df = pd.DataFrame(data, columns = ["Product Name", "URL", "Price", "D-Price", "Store", "Image Url"])
df.to_csv('trendyol3.csv')
>Solution :
You should add mode='a', which means append to append to file instead of rewriting:
df.to_csv('trendyol3.csv', mode='a')