0
属性urlからurlを取得するにはどうすればいいですか?高さ:510px;背景画像:のURL(https://cs7056.vk.me/c635104/v635104607/1c316/ADzy-2WY8pw.jpg)あなたのために」Selenium3のpython3は簡単にその特定のケースでSelenium3 Python3属性のスタイル= "background-image:ur、"からurlを取得する方法とURLがある "
import requests
from bs4 import BeautifulSoup
from selenium import webdriver
from selenium.webdriver.common.by import By
from selenium.webdriver.common.keys import Keys
from selenium.common.exceptions import NoSuchElementException
from selenium.common.exceptions import NoAlertPresentException
import re
import time
url = 'https://vk.com/uporols_you'
driver = webdriver.Firefox(executable_path='C:/Users/PANDEMIC/AppData/Local/Mozilla/geckodriver.exe')
def login(driver):
log_page = driver.get('https://login.vk.com/?act=login')
find_login_input = driver.find_element_by_id('login_form').find_element_by_id('email').send_keys('+77782303865')
find_password_input = driver.find_element_by_id('login_form').find_element_by_id('pass').send_keys('pass')
find_button = driver.find_element_by_xpath('//button[@id="login_button"]').click()
time.sleep(5)
def get_photo_from_page(driver):
driver.get(url)
try:
driver.find_element_by_class_name('popup_box_container').find_element_by_class_name('box_title_wrap').find_element_by_class_name('box_x_button').click()
except:
print('nope nothing')
for i in range(2):
scrol_down = driver.find_element_by_id('public_wall').find_element_by_id('wall_more_link').click()
time.sleep(2)
tut = []
#t = (a[@class="page_post_thumb_wrap image_cover page_post_thumb_last_column page_post_thumb_last_row"])
for ii in driver.find_elements_by_xpath('//a[@style]'):
o = ii.get_attribute('style')
print(o)
#soup = BeautifulSoup(htlm, 'lxml')
#im = soup.find_all('a', class_="'page_post_thumb_wrap image_cover page_post_thumb_last_column page_post_thumb_last_row'")
#print(htlm)
#for a in im:
# s = a.get('data-src_big').split('|')[0]
# tut.append(s)
#print(tut)
#for num, link in enumerate(tut, start=1):
# p = requests.get(link)
# out = open("img%s.jpg" % (num), 'wb')
# out.write(p.content)
# out.close()
def main():
login(driver)
get_photo_from_page(driver)
if __name__ == '__main__':
main()
が、どのようにこの[なし、なし、なし、なし、「https://pp.vk.me/c638718/v638718210/1b8a6/Fwbewm68Algを削除しないように。 jpg '、from this' https://cs7056.vk.me/c635104/v635104607/105ca/AmvyePsSzyM.jpg '、 –
リストの理解を使ってNoneを取り除くことができます。私の答えの編集を見てください。 –