# -*- coding:utf-8 -*-from selenium import webdriverfrom selenium.webdriver.common.keys import Keysimport timeimport reimport xlsxwriter
driver = webdriver.Chrome() # 打开Chrome浏览器driver.get("https://blog.csdn.net/xxxxxx") # 进入博客首页,这里是csdn博客，xxxxx是博主昵称
time.sleep(1)driver.maximize_window() # 最大化窗口
# 获取博客总页数listNum = driver.find_element_by_id("pageBox").textprint(listNum)number = re.sub("\D", "", listNum)number1 = list(number)print(number)print(number1)number2 = [int(i) for i in number1]print(number2)max_number = max(number2)print(max_number)
# 获取博客标题time.sleep(2)mylist = []workbook = xlsxwriter.Workbook('./data.xlsx') # 获取的标题保存到当前目录的data.xlsxworksheet = workbook.add_worksheet()bold_format = workbook.add_format({'bold': True}) # 加粗
# excel表格表头设计，保存六页数据worksheet.write('A1', u'第一页', bold_format)worksheet.write('B1', u'第二页', bold_format)worksheet.write('C1', u'第三页', bold_format)worksheet.write('D1', u'第四页', bold_format)worksheet.write('E1', u'第五页', bold_format)worksheet.write('F1', u'第六页', bold_format)row = 1col = 0try: for j in range(1, max_number): time.sleep(2) print("============第 %d 页数据==========" % j) for i in range(1, 41): mylist1 = driver.find_element_by_xpath(".//*[@id='mainBox']/main/div[2]/div["+str(i)+"]/h4/a").text # # 获取博客标题名称 print(mylist1) worksheet.write_string(row + i, col + j - 1, str(mylist1)) time.sleep(2) target = driver.find_element_by_xpath("html/body/div[6]/main/div[2]/div[41]/div/ul/li[9]") # 找到“下一页”元素 driver.execute_script("arguments[0].scrollIntoView();", target) # 拖动滚动条到指定的元素位置 time.sleep(1) target.click() # 下一页数据 driver.quit() # 关闭浏览器 workbook.close()except Exception as e: print("出错了,原因为:", e) driver.quit() # 关闭浏览器 workbook.close()
评论