نقوم بتحليل السيرة الذاتية للمحامين على hh.ru بدون واجهة برمجة تطبيقات

from selenium import webdriver
import time,csv
browser = webdriver.Firefox()
time.sleep (5) #   -  
browser.get ('https://hh.ru/employer')
time.sleep (5)

a = browser.find_element_by_css_selector('.bloko-icon_cancel')
a.click()
time.sleep (2)
a=browser.find_element_by_css_selector('div.supernova-navi-item:nth-child(6) > a:nth-child(1)')
a.click()
time.sleep (3)    
emailElem = browser.find_element_by_css_selector('.HH-AuthForm-Login')
emailElem.click()
time.sleep (1)
emailElem.send_keys('example@yandex.ru')    
time.sleep (1)
passElem = browser.find_element_by_css_selector('.HH-AuthForm-Password')
passElem.click()
time.sleep (1)
passElem.send_keys('password')
passElem.submit()
time.sleep (3)

def write_csv(data):
    with open('hh.csv','a',encoding='utf8') as f:
        writer=csv.writer(f)
        writer.writerow((data['name'],
                         data['age'],
                         data['salary'],                         
                         data['stag'],
                         #data['post_job_place'],
                         data['resume_link'],
                         data['photo_big']
                         #data['job_places'],
                         #data['education'],
                         #data['address'],
                         #data['update']
                         )) 

def resume_get():    
    # 
    a=browser.find_elements_by_class_name('resume-search-item__content-wrapper') # 100 
    #len(a)
    #resume-search-item__description-content -  
    for i in a:
        b=i.find_element_by_class_name('resume-search-item__header')
        name=b.find_element_by_class_name('resume-search-item__name').text # 
        age=b.find_element_by_class_name('resume-search-item__fullname').text # 52 
        salary=b.find_element_by_class_name('resume-search-item__compensation').text # 40000 .
        stag=i.find_elements_by_class_name('resume-search-item__description-content')[0].text # '7   8 '
        resume_link=i.find_element_by_class_name('resume-search-item__name').get_attribute('href') #  
        #post_job_place=i.find_elements_by_class_name('resume-search-item__description-content')[1].text #.  
        #job_places=b.find_elements_by_class_name('resume-search-item__description-content')[1:3] # 
        #education=i.find_elements_by_class_name('resume-search-item__description-content')[-1].text # 
        #photo_small=browser.find_element_by_class_name('resume-userpic').find_element_by_class_name('resume-userpic__photo').get_attribute('src') #   
        try:
            photo_big=i.find_element_by_class_name('bloko-modal-content').find_element_by_tag_name('img').get_attribute('src') #  -
        except:
            photo_big=''

     
        #update=i.find_element_by_class_name('output__addition').text #  
        data={    'name':name,
                  'age':age,
                  'salary':salary,
                  'stag':stag,                  
                  #'post_job_place':post_job_place,
                  'resume_link':resume_link,
                  'photo_big':photo_big
                  #'job_places':job_places,
                  #'education':education,
                  #'address':address,
                  #'update':update
                  }
        #print(data)
        write_csv(data)

resume_get()
x=0

while x!=50:
    browser.get (url+'&page='+str(x+1))
    time.sleep(7)
    resume_get()
    x+=1