51 data analysis post

51 Data analysis position

import csv
import time

from selenium import webdriver
from selenium.webdriver.common.keys import Keys
from selenium.webdriver.common.by import By


#  Launch the browser 
browser = webdriver.Chrome()
#  Access to web site 
browser.get('https://www.51job.com/')
#  Open window size 
browser.set_window_size(1000, 800)

#  Delay waiting 
browser.implicitly_wait(10)
#  Find the search box 
search_input = browser.find_element(By.ID, 'kwdselectid')
#  Enter search content 
search_input.send_keys(' Data analysis ')
#  Click enter 
search_input.send_keys(Keys.ENTER)

#  Select crawl data page 
for page in range(1, 2):
    browser.implicitly_wait(10)
    #  Sleep for a second 
    time.sleep(1)
    #  Position 
    titles = browser.find_elements(By.CSS_SELECTOR,
            'body > div:nth-child(4) > div.j_result > div > div.leftbox > div:nth-child(4) > div.j_joblist > div > a > p.t > span.jname.at')
    #  Company name 
    names = browser.find_elements(By.CSS_SELECTOR,
            'body > div:nth-child(4) > div.j_result > div > div.leftbox > div:nth-child(4) > div.j_joblist > div > div.er > a')
    #  Company type 
    business = browser.find_elements(By.CSS_SELECTOR,
            'body > div:nth-child(4) > div.j_result > div > div.leftbox > div:nth-child(4) > div.j_joblist > div > div.er > p.int.at')
    #  Company conditions 
    claims = browser.find_elements(By.CSS_SELECTOR,
            'body > div:nth-child(4) > div.j_result > div > div.leftbox > div:nth-child(4) > div.j_joblist > div > a > p.info > span.d.at')
    #  Release time 
    release_times = browser.find_elements(By.CSS_SELECTOR,
            'body > div:nth-child(4) > div.j_result > div > div.leftbox > div:nth-child(4) > div.j_joblist > div > a > p.t > span.time')
    for title, name, busines, claim, release_time in zip(titles, names, business, claims, release_times):
        print(' Position ：', title.text)
        print(' Company name ：', name.text)
        print(' Company type ：', busines.text)
        print(' Conditions ：', claim.text)
        print(' Release time ：', release_time.text)
        #  Save crawl data as CSV File for 
        with open(r'51job Data analysis position .csv', 'a', encoding='utf-8') as file:
            writer = csv.writer(file)
            writer.writerow([title.text, name.text, busines.text, claim.text, release_time.text])
    if page < 1:
        #  Click next 
        browser.find_element(By.XPATH, '/html/body/div[2]/div[3]/div/div[2]/div[4]/div[2]/div/div/div/ul/li[last()]/a').click()
    else:
        break