Question

我有下面的代码从网页中提取出一段HTML元素。我需要使用检索到的元素创建一个新的html文档。任何建议都一样。

options = webdriver.ChromeOptions()
driver = webdriver.Chrome(executable_path=r'C:\chromedriver_win32\chromedriver.exe', chrome_options=options)
driver.implicitly_wait(10)
driver.get("https://mylink") #original link from where I am retrieving other web links
elems = driver.find_elements_by_css_selector("[href*=PublicInfoServlet]")#Looking for other weblinks and storing in this variable
for elem in elems:
    abc=elem.get_attribute("href") #iterating over all the weblinks retrieved.
    print(abc)
    page = urllib.request.urlopen(abc)
    soup = BeautifulSoup(page,'html.parser')


    a=soup.find("div", {"id": "SPrint"}) #extracting the elements under the DIV id Sprint.

    print(a)

如何使用变量（a）下捕获的值创建新的html文档？

Answer 1

仅进行了少量研究，就可以找到解决方案。

from selenium import webdriver
import urllib.request,os,datetime
from bs4 import BeautifulSoup

options = webdriver.ChromeOptions()
driver = webdriver.Chrome(executable_path=r'C:\chromedriver_win32\chromedriver.exe', chrome_options=options)
driver.implicitly_wait(10)
driver.get("https://mylink")
elems = driver.find_elements_by_css_selector("[href*=PublicInfoServlet]") #finding the weblinks(html doc) I need to edit and create new html docs
for elem in elems: #iterate through all the html weblinks found on the main webpage
    abc=elem.get_attribute("href")
    print(abc)
    page = urllib.request.urlopen(abc)
    soup = BeautifulSoup(page,'html.parser')
    a=soup.find("div", {"id": "SpanPrint"}) #identify the html tag that needs to be used to create the required html document
    efg = (abc.split("=", 1)[1])
    hig=(efg.split('&', 1)[0])
    f = open(str(hig)+'.html', 'w')
    message=str(a)
    f.write(message)
    f.close()

    # Change path to reflect file location
    x = str(datetime.date.today())
    b = str(datetime.datetime.now())
    c = x[0:10]
    d = b[11:19]
    e = str(c + d).replace(':', '')
    filename = 'mypath' +str(hig)+'.html' #saving the new doc at the required location.
    os.rename('mypath'.html',
              'mypath' +str(hig) + e + '.html')
driver.quit()

使用python创建HTML文档

1 个答案: