1. from selenium import webdriver
    2. from selenium.webdriver.common.by import By
    3. from selenium.webdriver.support.ui import WebDriverWait
    4. from selenium.webdriver.common.keys import Keys
    5. from selenium.webdriver.support import expected_conditions as EC
    6. from selenium.webdriver.chrome.options import Options
    7. import time
    8. import csv
    11. class BOSSjob():
    12.     position_list = []
    13.     num = 0
    14.     def __init__(self):
    15.         # self.option = webdriver.ChromeOptions()
    16.         self.option = Options()
    17.         self.option.add_argument('--headless')
    18.         self.driver = webdriver.Chrome()
    19.         self.url = 'https://www.zhipin.com/chengdu/?sid=sem_pz_bdpc_dasou_title'
    20.         self.driver.get(self.url)
    21.         self.driver.find_element(By.XPATH, '//div[@class="search-form-con"]/p[@class="ipt-wrap"]/input').send_keys(
    22.             'java开发工程师')
    23.         self.driver.find_element(By.XPATH, '//div[@class="search-form "]/form/button[1]').click()
    24.         # self.element = WebDriverWait(self.driver, 3).until(
    25.         #     EC.presence_of_element_located(By.XPATH, '//div[@class="search-form-con"]/p[@class="ipt-wrap"]/input')
    26.         # )
    27.         # self.element.send.keys('java开发')
    28.         time.sleep(2)
    30.     def Parsedata(self):
    31.         self.driver.execute_script(
    32.             'window.scrollTo(0, document.body.scrollHeight)'
    33.         )
    34.         # source = self.driver.page_source
    35.         posi_li = self.driver.find_elements(By.XPATH, '//div[@class="job-list"]/ul/li')
    36.         for li in posi_li:
    37.             try:
    38.                 posi_dict = {}
    39.                 # 职位名称
    40.                 posi_dict['position'] = li.find_element(
    41.                     By.XPATH,
    42.                     './/div[@class="job-primary"]/div[@class="info-primary"]/div[@class="primary-wrapper"]/div[@class="primary-box"]/div[@class="job-title"]/span/a'
    43.                 ).text
    44.                 # 地址
    45.                 posi_dict['address'] = li.find_element(
    46.                     By.XPATH,
    47.                     './/div[@class="job-primary"]/div[@class="info-primary"]/div[@class="primary-wrapper"]/div[@class="primary-box"]/div[@class="job-title"]/span[2]/span'
    48.                 ).text
    49.                 # 薪资
    50.                 posi_dict['salary'] = li.find_element(
    51.                     By.XPATH,
    52.                     './/div[@class="job-primary"]/div[@class="info-primary"]/div[@class="primary-wrapper"]/div[@class="primary-box"]/div[@class="job-limit clearfix"]/span'
    53.                 ).text
    54.                 # 公司名称
    55.                 posi_dict['company'] = li.find_element(
    56.                     By.XPATH,
    57.                     './/div[@class="job-primary"]/div[@class="info-primary"]/div[@class="info-company"]/div[@class="company-text"]/h3[@class="name"]/a'
    58.                 ).text
    59.                 posi_dict['skills'] = '/'.join(li.find_element(
    60.                     By.XPATH,
    61.                     './/div[@class="job-primary"]/div[@class="info-append clearfix"]/div[@class="tags"]'
    62.                 ).text.split())
    64.                 BOSSjob.position_list.append(posi_dict)
    65.             except Exception as e:
    66.                 BOSSjob.num += 1
    67.                 print(e)
    69.     def Savedata(self):
    70.         with open('BOSS.csv', 'w', encoding='utf-8-sig', newline='') as f:
    71.             writer = csv.DictWriter(f, fieldnames=('position', 'address', 'salary', 'company', 'skills'))
    72.             writer.writeheader()
    73.             writer.writerows(BOSSjob.position_list)
    75.     def main(self):
    76.         for conut in range(5):
    77.             self.Parsedata()
    78.             self.driver.implicitly_wait(2)
    79.             tag = self.driver.find_element(By.XPATH, '//div[@class="page"]/a[@class="next"]')
    80.             self.driver.execute_script('arguments[0].click()', tag)
    81.         self.driver.quit()
    82.         self.Savedata()
    83.         print(BOSSjob.num)
    85. if __name__ == '__main__':
    86.     job = BOSSjob()
    87.     job.main()