基于pythonrequestsselenium爬取excelvba过程解析

#
# parent 上级节点
# wait_text 上级节点对应的xpath路径的文本项
# level,limit 仅方便测试使用
#
def GetMenuDick_jstree(parent,level,wait_text,limit=2):
  if level >= limit: return []
  parent.click()
  l = []
  num = 1
  new_wati_text = wait_text + '/following-sibling::ul' # 只需要等待ul出来就可以了/li[' + str(ele_num) + ']'
  try:
    wait.until(EC.presence_of_element_located((By.XPATH,new_wati_text)))
    # 查询子节点所有的 a节点和span节点（子菜单）
    childs = parent.find_elements_by_xpath('following-sibling::ul/li/span | following-sibling::ul/li/a')
    for i in childs:
      k = {}
      if i.get_attribute('role') == None:
        k['text'] = i.text
        # 如果是子菜单，进行深度遍历
        k['children'] = GetMenuDick_jstree(i,level+1,new_wati_text + '/li[' + str(num) + ']/span',limit)
      else:
        # 网页访问的Url无Html后缀，需要加上。去除无相关地址，形成相对路径。
        url_text = str(i.get_attribute('href')).replace('https://docs.microsoft.com/zh-cn/office/', '',1) + '.html'
        k['text'] = i.text
        k['a_attr'] = {"href":url_text,"target":"showframe"}
        lhref.append(str(i.get_attribute('href')))
      num = num + 1
      l.append(k)
    parent.click()  # 最后收起来
  except Exception as e:
    print('error message:',str(e),'error parent:' ,parent.text,' new_wati_text:',new_wati_text,'num:',str(num))
    lerror.append(parent.text)
  finally:
    return l

# data菜单，lhref为后续需要访问的地址。
# 找到第一个excel节点，从excel开始
data = []
lhref = []
lerror = []
k = {}
browser.get(start_url)
browser.set_page_load_timeout(10)  #超时设置
xpath_text = '//li[contains(@class,"tree")]/span[text()="Excel"][1]'
cl = browser.find_element_by_xpath(xpath_text)
k = {'text':'Excel'}
k['children'] = GetMenuDick_jstree(cl,1,xpath_text,20)
data.append(k)
# Writing JSON data
with open(r'templete\data.json', 'w', encoding='utf-8') as f:
  json.dump(data, f)

#
#  根据网页地址，得到文件名，并创建相应文件夹
#
def create_file(url):
  t = 'https://docs.microsoft.com/zh-cn/office/'
  # 替换掉字眼，然后根据路径生成相应文件夹
  url = url.replace(t,"",1)
  lname = url.split('/')
  # 先判断有没有第一个文件夹
  path = lname[0]
  if not os.path.isdir(path):
    os.mkdir(path)
  for l in lname[1:-1]:
    path = path + '\\' + str(l)
    if not os.path.isdir(path):
      os.mkdir(path)
  if len(lname) > 1:
    path = path + '\\' + lname[-1] + '.html'
  return path

# requests模式
# 循环遍历,如果错误，记录下来，以后再执行
had_lhref = []
error_lhref = []
num = 1
for url in lhref:
  try:
    had_lhref.append(url)
    path = create_file(url)
    resp = requests.get(url,timeout=5,headers = headers) # 设置访问超时，以及http头
    resp.encoding = 'utf-8'
    html = etree.HTML(resp.text)
    c = html.xpath('//main[@id="main"]')
    # tostring获取标签所有html内容，是字节类型，要decode为字符串
    cOntent= html_head + etree.tostring(c[0], method='html').decode('utf-8')
    with open(path,'w', encoding='utf-8') as f:
      f.write(content)
  except Exception as e:
    print('error message:',str(e),'error url:',url)
    error_lhref.append(url)
  if num % 10 == 0 :
    print('done:',str(num) + '/' + str(len(lhref)),'error num:' + str(len(error_lhref)))
  #time.sleep(1) # 睡眠一下，防止被反
  num = num + 1

  
  
  
  
  
  



  


    
      
      Search