Код: Выделить всё
# importing modules
import pandas as pd
from requests import get
from bs4 import BeautifulSoup
# Fetch the web page
url = 'https://www.backmarket.com/en-us/r/l/airpods/345c3c05-8a7b-4d4d-ac21-518b12a0ec17'
response = get(url) # link exlcudes posts with no picures
page = response.text
# Parse the HTML content
soup = BeautifulSoup(page, 'html.parser')
# To see different information
## reviewer's name
reviewers_name = soup.find_all('p', class_='body-1-bold')
[x.text for x in reviewers_name]
name = []
for items in reviewers_name:
name.append(items.text if items else None)
## Purchase Data
purchase_date = soup.find_all('p', class_='text-static-default-low body-2')
[x.text for x in purchase_date]
date = []
for items in purchase_date:
date.append(items.text if items else None)
## Country
country_text = soup.find_all('p', class_='text-static-default-low body-2 mt-32')
[x.text for x in country_text]
country = []
for items in country_text:
country.append(items.text if items else None)
## Reviewed Products
products_text = soup.find_all('span', class_= 'rounded-xs inline-block max-w-full truncate body-2-bold px-4 py-0 bg-static-default-mid text-static-default-hi')
[x.text for x in products_text]
products = []
for items in products_text:
products.append(items.text if items else None)
## Actual Reviews
review_text = soup.find_all('p',class_='body-1 block whitespace-pre-line')
[x.text for x in review_text]
review = []
for items in review_text:
review.append(items.text if items else None)
## Review Ratings
review_ratings_value = soup.find_all('span',class_='ml-4 mt-1 md:mt-2 body-2-bold')
[x.text for x in review_ratings_value]
review_ratings = []
for items in review_ratings_value:
review_ratings.append(items.text if items else None)
# Create the Data Frame
pd.DataFrame({
'reviewers_name': name,
'purchase_date': date,
'country': country,
'products': products,
'review': review,
'review_ratings': review_ratings
})
Подробнее здесь: https://stackoverflow.com/questions/790 ... er-reviews
