python网络数据采集17 docx

[python]代码库

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)

[代码运行效果截图]