Python XML.iter方法代码示例

# 需要导入模块: from xml.etree.cElementTree import XML [as 别名]
# 或者: from xml.etree.cElementTree.XML import iter [as 别名]
def parse_config(soup):
    """There are lots of goodies in the config we get back from the ABC.
    In particular, it gives us the URLs of all the other XML data we
    need.
    """

    xml = XML(soup)
    params = dict()
    for param in xml.iter('param'):
        params.setdefault(param.get('name'), param.get('value'))

    # should look like "rtmp://cp53909.edgefcs.net/ondemand"
    # Looks like the ABC don't always include this field.
    # If not included, that's okay -- ABC usually gives us the server in the auth result as well.
    rtmp_url = params['server_streaming']
    categories_url = params['categories']

    params.update({
        'rtmp_url'  : rtmp_url,
        'auth_url'  : params['auth'],
        'api_url' : params['api'],
        'categories_url' : categories_url,
        'captions_url' : params['captions'],
    })
    return params

# 需要导入模块: from xml.etree.cElementTree import XML [as 别名]
# 或者: from xml.etree.cElementTree.XML import iter [as 别名]
def parse_captions(soup):
    """Converts custom iView captions into SRT format, usable in most
    decent media players.
    """
    
    # Horrible hack to escape literal ampersands, which have been seen in
    # some captions XML. Inspired by
    # http://stackoverflow.com/questions/6088760/fix-invalid-xml-with-ampersands-in-python
    if b"<![CDATA[" not in soup:  # Not seen, but be future proof
        soup = re.sub(b"&(?![#\w]+;)", b"&amp;", soup)
    
    xml = XML(soup)

    output = ''

    i = 1
    for title in xml.iter('title'):
        start = title.get('start')
        (start, startfract) = start.rsplit(':', 1)
        end = title.get('end')
        (end, endfract) = end.rsplit(':', 1)
        output = output + '{}\n'.format(i)
        output = output + '{},{:0<3.3} --> {},{:0<3.3}\n'.format(start, startfract, end, endfract)
        output = output + title.text.replace('|','\n') + '\n\n'
        i += 1

    return output

# 需要导入模块: from xml.etree.cElementTree import XML [as 别名]
# 或者: from xml.etree.cElementTree.XML import iter [as 别名]
def get_docx_text(path):
    #use white-space: pre CSS
    """
    Take the path of a docx file as argument, return the formatted text.
    """
    document = zipfile.ZipFile(path)
    xml_content = document.read('word/document.xml')
    document.close()
    tree = XML(xml_content)
    
    #elements = list()
    styleAdditions = list()
    elementString = ["<article>"]
	
    for paragraph in tree.iter(PARA):
        """for paraStyleElement in paragraph.find(PARAPROPS).iter():
            if paraStyleElement =="""
		
		#JUSTIFICATION
        justificationInfo = paragraph.find(PARAPROPS).find(justification).attrib[WORD_NAMESPACE+"val"]
        if justificationInfo != "left" and justificationInfo != "both":
            styleAdditions.append("text-align:"+justificationInfo+";")
        elif justificationInfo == "both":
            styleAdditions.append("text-align:justify;")
		
		#INDENT
        if paragraph.find(PARAPROPS).find(indent):
            indentInfo = dict()
            for attribKey in paragraph.find(PARAPROPS).find(indent).attrib:
                if attribKey == WORD_NAMESPACE +"hanging":
                    indentInfo["hanging"] = (float(paragraph.find(PARAPROPS).find(indent).attrib[attribKey])/20)
                if attribKey == WORD_NAMESPACE +"end" or attribKey == WORD_NAMESPACE +"right":
                    indentInfo["right"] = (float(paragraph.find(PARAPROPS).find(indent).attrib[attribKey])/20)
                if attribKey == WORD_NAMESPACE +"start" or attribKey == WORD_NAMESPACE +"left":
                   indentInfo["left"] = (float(paragraph.find(PARAPROPS).find(indent).attrib[attribKey])/20)
            for key in indentInfo:
                if key == "hanging":
                    styleAdditions.append("margin-top:"+str(indentInfo[key])+";")
                if key == "right" or key == "end":
                    styleAdditions.append("margin-right:"+str(indentInfo[key])+";")
                if key == "left" or key == "start":
                    styleAdditions.append("margin-left:"+str(indentInfo[key])+";")
                #left => start, right => end, hanging
				
		#BACKGROUND COLOURING
        if paragraph.find(PARAPROPS).find(shade):
                if paragraph.find(PARAPROPS).find(shade).attrib[WORD_NAMESPACE +"fill"] != "auto":
                    styleAdditions.append("background-color: #"+paragraph.find(PARAPROPS).find(shade).attrib["fill"]+";")
                
		#BORDERS
        if paragraph.find(PARAPROPS).find(paraBorders):
            for sideElement in paragraph.find(PARAPROPS).find(paraBorders).iter():
                pass
                if sideElement != WORD_NAMESPACE + "between":
                    styleAdditions.append("border-style:"+borderTypes[sideElement.attrib["val"]])
                        
		#GET ALL THE TEXT, FIX TO PUT TEXT INTO ITS HTML ELEMENT
        paragraphText = [element.text for element in paragraph.iter(TEXT) if element.text] #make a list comprehension of styles to match
        if not paragraphText:
            if paragraph.iter(shdBreak):            
                for shadow in paragraph.iter(shdBreak): #bloody generator making me use a for loop for one element
                    if shadow.attrib[WORD_NAMESPACE+"fill"] == "auto":
                        for element in paragraph.iter(fontSize):
                            breakSize = str(float(element.attrib[WORD_NAMESPACE+"val"])/2) #gets a dict of fontSize element attributes, then gets the value representing font size, in points
                            break
                        styleAdditions.append("min-height:"+breakSize+"pt;") #why not em? ATTENTION ATTENTION ATTENTION ATTENTION ATTENTION
                        styleAdditions.append("margin:0;")
                    break
        else:
            elementString.append("<p")
            elementString.append(' style="')
            #elementString.append("white-space:pre-wrap;word-wrap:break-word;")
            for style in styleAdditions:
                elementString.append(style)
            if ''.join(elementString)[-1:] != ";":
                elementString.append(";")
            
            elementString.append('"')
            elementString.append(">")
            elementString.append("</p>\n")
            styleAdditions = list()
        """texts = [node.text
                 for node in paragraph.iter(TEXT)
                 if node.text]
        if texts:
            elements.append(''.join(texts))"""
    elementString.append("</article>")
    return ''.join(elementString)