如何使用异步编程使硒更快？

Question

我的目标是在Khan Academy上刮取尽可能多的个人资料链接。然后在每个配置文件上抓取一些特定数据，以将其写入CSV文件。

这是脚本：

from selenium import webdriver
from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
from selenium.common.exceptions import TimeoutException,StaleElementReferenceException
from bs4 import BeautifulSoup
import re
from requests_html import HTMLSession

session = HTMLSession()
r = session.get('https://www.khanacademy.org/computing/computer-programming/programming#intro-to-programming')
r.html.render(sleep=5)
soup=BeautifulSoup(r.html.html,'html.parser')

#find course steps links
courses_links = soup.find_all(class_='link_1uvuyao-o_O-nodeStyle_cu2reh-o_O-nodeStyleIcon_4udnki')
list_courses={}

for links in courses_links:
    courses = links.extract()
    link_course = courses['href']
    title_course= links.find(class_='nodeTitle_145jbuf')
    span_title_course=title_course.span
    text_span=span_title_course.text.strip()
    final_link_course ='https://www.khanacademy.org'+link_course
    list_courses[text_span]=final_link_course


# my goal is to loop the below script with each "course link" that I got above with list_courses
for courses_step in list_courses.values():
    driver = webdriver.Chrome()
    driver.get(courses_step)
    while True:
        try:
            showmore=WebDriverWait(driver, 15).until(EC.presence_of_element_located((By.CLASS_NAME,'button_1eqj1ga-o_O-shared_1t8r4tr-o_O-default_9fm203')))
            showmore.click()
        except TimeoutException:
            break
        except StaleElementReferenceException:
            break

    soup=BeautifulSoup(driver.page_source,'html.parser')
    #find the profile links
    profiles = soup.find_all(href=re.compile("/profile/kaid"))
    profile_list=[]
    for links in profiles:
        links_no_list = links.extract()
        text_link = links_no_list['href']
        text_link_nodiscussion = text_link[:-10]
        final_profile_link ='https://www.khanacademy.org'+text_link_nodiscussion
        profile_list.append(final_profile_link)

    #remove duplicates
    profile_list=list(set(profile_list))

    #print number of profiles we got
    print('in this link:')
    print(courses_step)
    print('we have this number of profiles:')
    print(len(profile_list))

    #create the csv file
    filename = "khan_mergetry4.csv"
    f = open(filename, "w")
    headers = "link, date_joined, points, videos, questions, votes, answers, flags, project_request, project_replies, comments, tips_thx, last_date\n"
    f.write(headers)

    #for each profile link, scrape the specific data and store them into the csv
    for link in profile_list:

        #print each profile link we are about to scrap
        print("Scrapping ",link)
        driver.get(link)

        #wait for content to load
        #if profile does not exist skip
        try:
            WebDriverWait(driver, 10).until(EC.presence_of_element_located((By.XPATH ,'//*[@id="widget-list"]/div[1]/div[1]')))
        except TimeoutException:
            continue
        soup=BeautifulSoup(driver.page_source,'html.parser')
        user_info_table=soup.find('table', class_='user-statistics-table')
        if user_info_table is not None:
            dates,points,videos=[tr.find_all('td')[1].text for tr in user_info_table.find_all('tr')]
        else:
            dates=points=videos='NA'

        user_socio_table=soup.find_all('div', class_='discussion-stat')
        data = {}
        for gettext in user_socio_table:
            category = gettext.find('span')
            category_text = category.text.strip()
            number = category.previousSibling.strip()
            data[category_text] = number

        full_data_keys=['questions','votes','answers','flags raised','project help requests','project help replies','comments','tips and thanks'] #might change answers to answer because when it's 1 it's putting NA instead
        for header_value in full_data_keys:
            if header_value not in data.keys():
                data[header_value]='NA'

        user_calendar = soup.find('div',class_='streak-calendar-scroll-container')
        if user_calendar is not None:
            last_activity = user_calendar.find('span',class_='streak-cell filled')
            try:
                last_activity_date = last_activity['title']
            except TypeError:
                last_activity_date='NA'
        else:
            last_activity_date='NA'
        f.write(link + "," + dates + "," + points.replace("," , "") + "," + videos + "," + data['questions'] + "," + data['votes'] + "," + data['answers'] + "," + data['flags raised'] + "," + data['project help requests'] + "," + data['project help replies'] + "," + data['comments'] + "," + data['tips and thanks'] + "," + last_activity_date + "\n")

如您所见，这是一个同步版本。

我的问题是此脚本太慢了。 （大概需要100多个小时才能完全执行）。

如何使其运行更快？ 如何使该脚本异步？ 我应该怎么做？ 我应该如何组织我的代码来做到这一点？ （也许多处理更适合吗？）