def getText(word_document_content):
""" @param[in] word_document_content the content of the html page to convert
@param[in] encoding the document encoding
@returns the text representation of the Web page
"""
_, html = pipe_content( CMD_CONV['doc'], word_document_content )
return html
def getText(word_document_content):
""" @param[in] word_document_content the content of the html page to convert
@param[in] encoding the document encoding
@returns the text representation of the Web page
"""
_, html = pipe_content(CMD_CONV['doc'], word_document_content)
return html
def getText(pdf_content):
""" @param[in] pdf_content the content of the html page to convert
@param[in] encoding the document encoding
@returns the text representation of the Web page
"""
_, text = pipe_content(CMD_CONV['pdf'], pdf_content)
return text
def getText(pdf_content):
""" @param[in] pdf_content the content of the html page to convert
@param[in] encoding the document encoding
@returns the text representation of the Web page
"""
_, text = pipe_content( CMD_CONV['pdf'], pdf_content )
return text
def getText(html_content, encoding="utf8"):
""" @param[in] html_content the content of the html page to convert
@param[in] encoding the document encoding
@returns the text representation of the Web page
"""
# check whether this is really a html file
if not "<" in html_content or not ">" in html_content:
return html_content
_, html = pipe_content(CMD_CONV['html'], html_content)
return html
def getText(html_content, encoding="utf8"):
""" @param[in] html_content the content of the html page to convert
@param[in] encoding the document encoding
@returns the text representation of the Web page
"""
# check whether this is really a html file
if not "<" in html_content or not ">" in html_content:
return html_content
_, html = pipe_content(CMD_CONV['html'], html_content)
return html