会python真的可以为所欲为0(回)
359天前
这里还有人吗1(回)
544天前这里还有人吗0(回)
544天前
每天面对着电脑屏幕，敲打键盘。我所面对的并不只是代码，而是一种生活方式。0(回)
768天前到处都是羊，不想上班0(回)
848天前
鸽子
0(回)
853天前from zipfile import ZipFile |
from urllib.request import urlopen |
from io import BytesIO |
from bs4 import BeautifulSoup |
wordFile = urlopen("http://pythonscraping.com/pages/AWordDocument.docx").read() |
wordFile = BytesIO(wordFile) # 转成二进制文件对象 |
document = ZipFile(wordFile) # 解压文件 |
xml_content = document.read('word/document.xml') |
wordObj = BeautifulSoup(xml_content.decode('utf-8'),'html.parser') |
textStrings = wordObj.findAll("w:t") |
for textElem in textStrings: |
closeTag = "" |
try: |
style = textElem.parent.previousSibling.find("w:pstyle") # 父标签的前一个 |
if style is not None and style["w:val"] == "Title": # 如果<w:pstyle w:val="Title"></w:pstyle>存在 |
print("<h1>") |
closeTag = "</h1>" |
except AttributeError: |
#不打印标签 |
pass |
print(textElem.text) |
print(closeTag) |
