driver = webdriver.Chrome()
driver.get("https://www.zhipin.com/web/geek/job?query=%E6%95%B0%E6%8D%AE%E5%88%86%E6%9E%90&city=100010000")
获取当前页面信息,一定要等待网页加载完成,针对反爬措施,要点手动与自动相结合,手动登录(自动难以实现),翻页可以自动,一定要注意到driver始终获取的是当前页面最新信息
elements = driver.find_elements(By.CSS_SELECTOR, ".job-card-wrapper")
jobinfo_csv(elements)
def jobTaglist(taglist):
strTaglist = ""
for el in taglist:
strTaglist += el.text+"*"
return strTaglist
def jobinfo_csv(elements):
jobInfo = {}
for element in elements:
jobInfo["job-name"] = element.find_element(By.CSS_SELECTOR, ".job-name").text
jobInfo['job-area'] = element.find_element(By.CSS_SELECTOR, ".job-area").text
jobInfo['salary'] = element.find_element(By.CSS_SELECTOR, ".salary").text
t = element.find_element(By.CSS_SELECTOR, ".job-card-footer .tag-list").find_elements(By.XPATH, "./li")
jobInfo['technologylist']= jobTaglist(t)
taglist = element.find_element(By.CSS_SELECTOR, ".tag-list").find_elements(By.XPATH, "./li")
jobInfo['taglist']= jobTaglist(taglist)
companyTaglist = element.find_element(By.CSS_SELECTOR, ".company-tag-list").find_elements(By.XPATH, "./li")
jobInfo['companyTaglist']= jobTaglist(companyTaglist)
jobInfo['company-name'] = element.find_element(By.CSS_SELECTOR, ".company-name").text
jobInfo['info-desc'] = element.find_element(By.CSS_SELECTOR, ".info-desc").text
pddata = pd.DataFrame([jobInfo])
pddata.to_csv('static.csv',mode='a',encoding='utf-8',header=False,index=False)
网友评论