2021数据科学就业市场最全分析：Python技能最重要，5到10年经验最吃香

import pandas as pdimport numpy as npfrom selenium import webdriverfrom selenium.common.exceptions import NoSuchElementExceptionchromepath = r'D:\Drivers\Chrome Driver\chromedriver.exe'url_list = []for i in range(1, 50):    print('Opening Search Pages ' + str(i))    page_url = 'https://jobportalexample.com/data-scientist-jobs-'+str(i)    driver = webdriver.Chrome(chromepath)    driver.get(page_url)    print('Accessing Webpage OK \n')    url_elt = driver.find_elements_by_class_name("fw500")    print('Success')
    for j in url_elt:        url = j.get_attribute("href")        url_list.append(url)
driver.close()

url_list_copy_cleaned = [i for i in url_list]out_company_df = pd.DataFrame(url_list_copy_cleaned, columns=['Website'])out_company_df.head()

jobs={'roles':[],     'companies':[],     'locations':[],     'experience':[],     'skills':[]}
driver = webdriver.Chrome(chromepath)for url in out_company_df['Website']:    driver.get(url)    try:        name_anchor = driver.find_element_by_class_name('pad-rt-8')        name = name_anchor.text        jobs['companies'].append(name)    except NoSuchElementException:        jobs['companies'].append(np.nan)
    try:        role_anchor = driver.find_element_by_class_name('jd-header-title')        role_name = role_anchor.text        jobs['roles'].append(role_name)    except NoSuchElementException:        jobs['roles'].append(np.nan)
    try:        location_anchor = driver.find_element_by_class_name('location')        location_name = location_anchor.text        jobs['locations'].append(location_name)    except NoSuchElementException:        jobs['locations'].append(np.nan)
    try:        experience_anchor = driver.find_element_by_class_name('exp')        experience = experience_anchor.text        jobs['experience'].append(experience)    except NoSuchElementException:        jobs['experience'].append(np.nan)
    try:        skills_anchor = driver.find_elements_by_class_name("chip")        each_skill = []        for skills in skills_anchor:            each_skill.append(skills.text)        jobs['skills'].append(each_skill)    except NoSuchElementException:        jobs['skills'].append(np.nan)driver.close()