Python XML.getiterator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 getiterator [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.getiterator('title'):
		start = title.get('start')
		ids = start.rfind(':')
		end = title.get('end')
		ide = end.rfind(':')
		output = output + str(i) + '\n'
		output = output + start[:ids] + ',' + start[ids+1:] + ' --> ' + end[:ide] + ',' + end[ide+1:] + '\n'
		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 getiterator [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.getiterator('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']
	rtmp_chunks = rtmp_url.split('/')

	return {
		'rtmp_url'  : rtmp_url,
		'rtmp_host' : rtmp_chunks[2],
		'rtmp_app'  : rtmp_chunks[3],
		'auth_url'  : params['auth'],
		'api_url' : params['api'],
		'categories_url' : params['categories'],
		'captions_url' : params['captions'],
	}

# 需要导入模块: from xml.etree.cElementTree import XML [as 别名]
# 或者: from xml.etree.cElementTree.XML import getiterator [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.getiterator('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 getiterator [as 别名]
def get_raw_text(pthFile):
	"""
	gets a path to a file as an argument and returns a list containing
	the paragraphs of the word document file
	"""
	
	"""
	Constants used to iterate over the XML tree
	"""
	WORD_NAMESPACE = '{http://schemas.openxmlformats.org/wordprocessingml/2006/main}'
	PARA = WORD_NAMESPACE + 'p'
	TEXT = WORD_NAMESPACE + 't'

	docWordDoc = zipfile.ZipFile(pthFile) #gets the documents of the word
	xmlContent = docWordDoc.read('word/document.xml') #access the xml file
	docWordDoc.close()
	treeXML = XML(xmlContent) #parses the xml content into a tree that will be further used to access the text

	lstParagraphs = [] #output list with the paragraphs of the text
	#now we proceed to extract the text from the tree
	#the idea is to iterate over the tree and 
	#for each node that contains text, substract it and add it to
	#the output
	for parParagraph in treeXML.getiterator(PARA):
		lstTexts = [nodElement.text
			    for nodElement in parParagraph.getiterator(TEXT)
			    if nodElement.text]
		if lstTexts:
			print lstTexts
			lstParagraphs.append(''.join(lstTexts))
		
	return lstParagraphs

# 需要导入模块: from xml.etree.cElementTree import XML [as 别名]
# 或者: from xml.etree.cElementTree.XML import getiterator [as 别名]
 def get_docx_text(self, path):
     document = zipfile.ZipFile(path)
     xml_content = document.read('word/document.xml')
     tree = XML(xml_content)
     document.close()
     paragraphs = []
     for paragraph in tree.getiterator(para_tag):
         texts = [node.text for node in paragraph.getiterator(text_tag) if node.text]
         if texts:
             paragraphs.append(''.join(texts))
     return paragraphs

# 需要导入模块: from xml.etree.cElementTree import XML [as 别名]
# 或者: from xml.etree.cElementTree.XML import getiterator [as 别名]
def get_docx_text(path):
    document = zipfile.ZipFile(path)
    xml_content = document.read("word/document.xml")
    document.close()
    tree = XML(xml_content)

    paragraphs = []
    for paragraph in tree.getiterator(PARA):
        texts = [node.text for node in paragraph.getiterator(TEXT) if node.text]
        if texts:
            paragraphs.append("".join(texts))
    return paragraphs

# 需要导入模块: from xml.etree.cElementTree import XML [as 别名]
# 或者: from xml.etree.cElementTree.XML import getiterator [as 别名]
def get_docx_text(path):
	"""
	Take the path of a docx file as argument, return the text in unicode
	in the form of a list.
	"""
	document = zipfile.ZipFile(path)
	xml_content = document.read('word/document.xml')
	document.close()
	tree = XML(xml_content)
 
	paragraphs = []
	for paragraph in tree.getiterator(PARA):
		texts = [node.text.encode('utf-8')
				 for node in paragraph.getiterator(TEXT)
				 if node.text]
		if texts:
			paragraphs.append(''.join(texts))
 
	return paragraphs



 
# def get_docx_text(path):
# 	"""
# 	Take the path of a docx file as argument, return the text in unicode
# 	in the form of a list.
# 	"""
# 	document = zipfile.ZipFile(path)
# 	xml_content = document.read('word/document.xml')
# 	document.close()
# 	tree = XML(xml_content)
 
# 	sections = []
# 	for section in tree.getiterator(SECT):

# 		paragraphs = []
# 		for paragraph in section.getiterator(PARA):
# 			print 'para'
# 			texts = [node.text.encode('utf-8')
# 					 for node in paragraph.getiterator(TEXT)
# 					 if node.text]
# 			if texts:
# 				paragraphs.append(''.join(texts))

# 		print str(paragraphs)

# 		if paragraphs:
# 			sections.append(''.join(paragraphs))

 
# 	return sections    

# 需要导入模块: from xml.etree.cElementTree import XML [as 别名]
# 或者: from xml.etree.cElementTree.XML import getiterator [as 别名]
def read_docx(file,document,path,trie):
	xml_content = document.read('word/document.xml')
	document.close()
	tree = XML(xml_content)
	paragraphs = ""
	for paragraph in tree.getiterator(PARA):
		texts=""
		for node in paragraph.getiterator(TEXT):
			if node.text:
				texts += node.text.replace('\u7460',"")
		if texts:
			paragraphs+=str(texts)
	#print(paragraphs)
	string_spilt(paragraphs,path,trie)
	trie.insert_doc_len(path,len(file)+len(paragraphs))

# 需要导入模块: from xml.etree.cElementTree import XML [as 别名]
# 或者: from xml.etree.cElementTree.XML import getiterator [as 别名]
def get_doc_text(path):
    """
    Take the path of a docx or a dot file as argument, return the text in unicode.
    """
    if "docx" == path[-4:]:
        document = zipfile.ZipFile(path)
        xml_content = document.read('word/document.xml')
        document.close()
        tree = XML(xml_content)
    #print tree

        paragraphs = []
        for paragraph in tree.getiterator(PARA):
            texts = [node.text for node in paragraph.iter(TEXT) if node.text]
            if texts:
                paragraphs.append(''.join(texts))
                pass
            pass
    #print paragraphs
        return paragraphs
#        
    elif "odt" == path[-3:]:
        document = zipfile.ZipFile(path)
        xml_content = document.read('content.xml')
        document.close()
        doc = xml.dom.minidom.parseString(xml_content)
        print(" doc: ",doc)
        print("doc::end")
        #paras = doc.getElementsByTagName('text:span')
        #paras = doc.getElementsByTagName('text:p')
        #
        # we get here all elements Headers, text and table components: 
        #
        paras = doc.getElementsByTagName("*")
        print("I have ", len(paras), " paragraphs ")
        paragraphs = []
        for p in paras:
            for ch in p.childNodes:
                if ch.nodeType == ch.TEXT_NODE:
                    paragraphs.append(''.join(ch.wholeText))
                    pass
                pass
            pass
        print(paragraphs)
        return paragraphs
    else:
        print() 
        raise Warning("only docx and odt files are handled")    

# 需要导入模块: from xml.etree.cElementTree import XML [as 别名]
# 或者: from xml.etree.cElementTree.XML import getiterator [as 别名]
def get_docx_text(path):
	"""	Take the path of a docx file as argument, return the text in unicode."""
	document = zipfile.ZipFile(path)
	xml_content = document.read('word/document.xml')
	document.close()
	tree = XML(xml_content)
 
	paragraphs = []
	for paragraph in tree.getiterator(PARA):
		texts = [node.text
				for node in paragraph.getiterator(TEXT)
				if node.text]
		if texts:
			paragraphs.append(''.join(texts))
 
	return '\n\n'.join(paragraphs) 

# 需要导入模块: from xml.etree.cElementTree import XML [as 别名]
# 或者: from xml.etree.cElementTree.XML import getiterator [as 别名]
def docx_do_docx(azip, afile):
    word_namespace = "{http://schemas.openxmlformats.org/wordprocessingml/2006/main}"
    par = word_namespace + "p"
    txt = word_namespace + "t"

    xml_content = azip.read("word/document.xml")
    tree = XML(xml_content)

    paragraphs = []
    for paragraph in tree.getiterator(par):
        texts = [node.text for node in paragraph.getiterator(txt) if node.text]
        if texts:
            paragraphs.append("".join(texts))

    text = "\n\n".join(paragraphs)
    text_do_data(text, afile)

# 需要导入模块: from xml.etree.cElementTree import XML [as 别名]
# 或者: from xml.etree.cElementTree.XML import getiterator [as 别名]
def docx_do_docx(azip, afile):
    namespace = '{http://schemas.openxmlformats.org/wordprocessingml/2006/main}'
    par = namespace + 'p'
    txt = namespace + 't'

    xml_content = azip.read('word/document.xml')
    tree = XML(xml_content)

    paragraphs = []
    for paragraph in tree.getiterator(par):
        texts = [node.text for node in paragraph.getiterator(txt)
                 if node.text]
        if texts:
            paragraphs.append(''.join(texts))

    text = '\n\n'.join(paragraphs)
    text_do_data(text, afile)

# 需要导入模块: from xml.etree.cElementTree import XML [as 别名]
# 或者: from xml.etree.cElementTree.XML import getiterator [as 别名]
    def getContents(self):
        """
        Just read the paragraphs from an XML file.
        """

        xml_content = self.my_docx.read('word/document.xml')
        self.my_docx.close()
        tree = XML(xml_content)

        self.text_in_paragraphs = []
        for paragraph in tree.getiterator(PARA):
            texts = [node.text for node in paragraph.iter(TEXT) if node.text]
            if texts:
                self.text_in_paragraphs.append(''.join(texts))
                pass
            pass
    #print paragraphs
        return self.text_in_paragraphs

# 需要导入模块: from xml.etree.cElementTree import XML [as 别名]
# 或者: from xml.etree.cElementTree.XML import getiterator [as 别名]
def parse_captions(soup):
	"""	Converts custom iView captions into SRT format, usable in most
		decent media players.
	"""
	xml = XML(soup)

	output = ''

	i = 1
	for title in xml.getiterator('title'):
		start = title.get('start')
		ids = start.rfind(':')
		end = title.get('end')
		ide = end.rfind(':')
		output = output + str(i) + '\n'
		output = output + start[:ids] + ',' + start[ids+1:] + ' --> ' + end[:ide] + ',' + end[ide+1:] + '\n'
		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 getiterator [as 别名]
def get_docx_text(path):
    """
    Take the path of a docx file as argument, return the text in unicode.
    """
    WORD_NAMESPACE = '{http://schemas.openxmlformats.org/wordprocessingml/2006/main}'   # formatting for docx
    PARA = WORD_NAMESPACE + 'p'                                                         # formatting for paragraphs
    TEXT = WORD_NAMESPACE + 't'                                                         # formatting for text
    document = zipfile.ZipFile(path)                                                    # the unzipped document path
    xml_content = document.read('word/document.xml')                                    # location of the primary xml document
    document.close()                                                                    # closes the document
    tree = XML(xml_content)                                                             # splits the xl into a tree

    paragraphs = []                                                                     # a list of the paragraphs
    for paragraph in tree.getiterator(PARA):                                            # for every new paragraph in the tree
        texts = [node.text                                                              # the text is the text node in the tree
                 for node in paragraph.getiterator(TEXT)                                # 
                 if node.text]                                                          # if the node is text, add it to the text list
        if texts:                                                                       # if a text is found,
            paragraphs.append(''.join(texts))                                           # add it to the paragraphs list
    #return('\n\n'.join(paragraphs))
    return(paragraphs)                                                                  # return the paragra