Парсер выдает пустой запрос

Question

пытаюсь запарсить с сайта марку автомобиля, год и цену, почему-то сохраняет пустой запрос. В чем может быть дело?

import requests
from bs4 import BeautifulSoup as bs
import pandas as pd

URL_TEMPLATE = "https://cars.av.by/bmw"
r = requests.get(URL_TEMPLATE)
FILE_NAME = "test.csv"


def parse(url = URL_TEMPLATE):
    result_list = {'mark': [],'year': [], 'price': []}
    r = requests.get(url)
    if (r.status_code == 403):
        print("Access denied")
    soup = bs(r.text, "html.parser")
    car_mark = soup.find_all('span', class_='link-text')
    car_year = soup.find_all('div', class_='listing-item__params')
    car_price = soup.find_all('div', class_='listing-item__price')
    for mark in car_mark:
        result_list['mark'].append(mark.text)
    for year in car_year:
        result_list['year'].append(year.text)
    for price in car_price:
        result_list['price'].append(price.text)
    return result_list


df = pd.DataFrame(data=parse())
df.to_csv(FILE_NAME)

Answer 1

у вас парсинг данных и его запись в CSV файл происходит для каждого элемента отдельно, вот исправленный код,попробуйте

import requests
from bs4 import BeautifulSoup as bs
import pandas as pd

URL_TEMPLATE = "https://cars.av.by/bmw"
r = requests.get(URL_TEMPLATE)
FILE_NAME = "test.csv"


def parse(url=URL_TEMPLATE):
    result_list = {'mark': [], 'year': [], 'price': []}
    r = requests.get(url)
    if r.status_code == 403:
        print("Access denied")
    soup = bs(r.text, "html.parser")
    car_mark = soup.find_all('span', class_='link-text')
    car_year = soup.find_all('div', class_='listing-item__params')
    car_price = soup.find_all('div', class_='listing-item__price')
    for mark in car_mark:
        result_list['mark'].append(mark.text)
    for year in car_year:
        result_list['year'].append(year.text)
    for price in car_price:
        result_list['price'].append(price.text)
    return result_list


df = pd.DataFrame(data=parse())
df.to_csv(FILE_NAME, index=False)`

Answer 2

import requests
from bs4 import BeautifulSoup as bs
import pandas as pd

URL_TEMPLATE = "https://cars.av.by/bmw"
FILE_NAME = "test.csv"
headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:123.0) Gecko/20100101 Firefox/123.0'}

def parse(url=URL_TEMPLATE):
    result_list = {}
    r = requests.get(url, headers=headers)
    if not r.ok:
    # if r.status_code == 403 or r.status_code == 423:
        print("Access denied")
        return {"Access denied": []}

    soup = bs(r.text, "html.parser")
    car_mark = soup.find_all('span', class_='link-text')
    result_list['mark'] = [x.text for x in car_mark]
    return result_list

df = pd.DataFrame(parse())
df.to_csv(FILE_NAME)

БЛОГ НА HUSL

Парсер выдает пустой запрос

Ответы (2 шт):