Selenium 爬取淘宝数据

1、项目流程

---

2、中心调度

# 中心调度

def main ():

try :

total = search()

total = int (re.compile( '.*?(\d+).*?' ).search(total).group( 1 ))

for i in range ( 2 ,total+ 1 ):

next_page(i)

except Exception as e :

print ( ' 异常 ' )

finally :

browser.close()

---

3、模拟查询

# 根据关键字查询

def search ():

try :

browser.get( 'https://www.taobao.com/' )

# 直到搜索框加载出

input_search = wait.until(EC.presence_of_element_located((By.ID, 'q' )))

# 直到搜索按钮可以点击

submit_button = wait.until(EC.element_to_be_clickable((By.CLASS_NAME, 'btn-search' )))

input_search.send_keys(KEYWORDS)

submit_button.click()

total = wait.until(EC.presence_of_element_located((By.CSS_SELECTOR, 'div.wraper div.total' )))

get_products()

return total.text

except TimeoutException as e :

print ( ' 响应超时 ' )

---

4、下一页的操作