Доброго дня
есть написаный парсинг :
import requests
from bs4 import BeautifulSoup
from selenium import webdriver
import csv
import os
URL = 'https://www.svyaznoy.ru/catalog/phone/8605/'
HEDARS = {'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_6) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/14.0.3 Safari/605.1.15', 'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8'}
FILE = 'svz.csv'
direct= os.getcwd()
def get_himl(url):
chromedriver =direct+'/chromedriver'
options = webdriver.ChromeOptions()
browser = webdriver.Chrome(executable_path=chromedriver,chrome_options=options)
browser.get(url)
generated_html = browser.page_source
browser.quit()
return generated_html
def seve_file(item,path):
with open(path, 'w', newline='',encoding='utf-8') as file:
writer = csv.writer(file, delimiter = ';')
writer.writerow(['модель', 'цена акция (без учета комбо)', 'акции', 'старая цена/цена без акции'])
for items in item:
writer.writerow([items['title'], items['prise'], items['action'], items['old_prise']])
def get_content(html):
soup = BeautifulSoup(html, 'html.parser')
items = soup.find_all('div', {'class': ["b-product-block__content"]})
phone =[]
p = len(items)
for items in items:
prise = items.find('span', class_="b-product-block__visible-price")
if prise:
prise = prise.get_text()
prise = prise.replace('\xa0', ' ')
else:
prise = "цена не указана"
sale = items.find('div', class_="b-product-block__action-info _old-price")
if sale:
sale = sale.get_text()
else:
sale = ""
actions = items.find('div', class_="b-product-block__action-info _action-price")
if actions:
actions = actions.get_text()
else:
actions = ""
discont = items.find('span', class_="discount-sum")
if discont:
discont = discont.get_text()
discont = "скидка по комбо: " + discont
else:
discont = ""
old_prise = items.find('s', class_="b-product-block__price-old")
if old_prise:
old_prise = old_prise.get_text()
old_prise = old_prise.replace('\xa0', ' ')
else:
old_prise = ""
oll_action = sale + " " + actions + " " + discont
if oll_action:
oll_action = oll_action
else:
oll_action = ''
pic_href = items.find('img', class_="lazy").get('content')
print(pic_href)
phone.append({
'title' : items.find('span', class_="b-product-block__name").get_text(),
'prise' : prise.replace('руб.', ' '),
'action' : oll_action,
'old_prise' : old_prise.replace('руб.', ' ')
})
return phone
def parsing():
phone = []
for page in range (1,3):
print(f'Анализ {page} ...')
a = URL + 'page-'+ str(page)
html = get_himl(a)
phone.extend(get_content(html))
seve_file(phone,FILE)
print(f'найдено ' + str(len(phone)) + ' телефонов')
parsing()
к нему захотел добавить извлечение картинок но при поиске ссылки выдает ошибку :
pic_href = items.find('img', class_="lazy").get('content')
print(pic_href)
File "/Users/alexs/Desktop/py/Parsing/parser_svz.py", line 70, in get_content
pic_href = items.find('img', class_="lazy").get('content')
AttributeError: 'NoneType' object has no attribute 'get'
подскажите что делаю не так?
