Linkedin 抓取，列表理解

Question

I am trying to get profile urls using list comprehension, but the list overwrites itself and I can't store urls from different pages, its stores only from the last page.

options = Options()
options.add_argument("--start-maximized")
# options.headless = True


url = "https://www.linkedin.com/login?fromSignIn=true&trk=guest_homepage-basic_nav-header-signin"
driver = webdriver.Chrome(r"path", options=options)

driver.get(url)
driver.find_element_by_id('username').send_keys('name')
driver.find_element_by_id('password').send_keys('pass', Keys.ENTER)
driver.implicitly_wait(10)
driver.find_element_by_class_name('search-global-typeahead__input').send_keys('Marketing manager', Keys.ENTER)
driver.implicitly_wait(10)
driver.find_element_by_xpath('//button[text()="People"]').click()


x = 0
profile = []
linklist = []
condition = True
while condition:
    sleep(2)
    driver.execute_script("window.scrollTo(0, 1400);")
    driver.implicitly_wait(10)
    linkedin_members = driver.find_elements_by_xpath('//span[@class="entity-result__title"]')
    links = [linkedin_member.find_element_by_xpath('.//a[@class="app-aware-link"]').get_attribute('href') for linkedin_member in linkedin_members if "/in/" in linkedin_member.find_element_by_xpath('.//a[@class="app-aware-link"]').get_attribute('href')]
    x = x + 1
    driver.implicitly_wait(10)
    if x == 3:
        condition = False
    driver.find_element_by_xpath("""//button[@class='artdeco-pagination__button artdeco-pagination__button--next artdeco-button artdeco-button--muted artdeco-button--icon-right artdeco-button--1 artdeco-button--tertiary ember-view' and contains(.,'Next')]""").click()

for l in links:
    driver.get(l)

Answer 1

You should append your information to a list outside the while loop for example:

links = [linkedin_member.find_element_by_xpath('.//a[@class="app-aware-link"]').get_attribute('href') for linkedin_member in linkedin_members if "/in/" in linkedin_member.find_element_by_xpath('.//a[@class="app-aware-link"]').get_attribute('href')]

#append result of listcomprehension to linklist
linklist.append(links)