def htm2txt(inf):
""" extract the text context"""
doc=html.document_fromstring(inf)
content=doc.xpath('//*[@id="contents"]')
htmls=html.tostring(content[0],False)
htmls=htmls.replace('<br>','\n')
htmls=htmls.replace('<p>','\n')
htmls=unescape(htmls)
p=re.compile('\n{2,}') #replace more than 2 newlines in a row into one newline
htmls=p.sub('\n',htmls)
newdoc=html.document_fromstring(htmls)
return newdoc.text_content()
def htm2txt(inf):
""" extract the text context"""
doc=html.document_fromstring(inf)
content=doc.xpath('//*[@id="bgdiv"]/table[2]/tbody/tr[1]/td/table/tbody/tr')
htmls=html.tostring(content[0],False)
htmls=htmls.replace('<br>','\n')
htmls=htmls.replace('<p>','\n')
htmls=htmls.replace(' ',' ')
p=re.compile('\n{2,}') #replace more than 2 newlines in a row into one newline
htmls=p.sub('\n',htmls)
newdoc=html.document_fromstring(htmls)
return newdoc.text_content()
def htm2txt(inf):
""" extract the text context"""
doc = html.document_fromstring(inf)
#content=doc.xpath('//*[@id="bgdiv"]/table[2]/tbody/tr[1]/td/table/tbody/tr')
content = doc.xpath('//*[@id="content"]')
htmls = html.tostring(content[0], False)
htmls = htmls.replace('<br>', '\n')
htmls = htmls.replace('<p>', '\n')
htmls = htmls.replace(' ', ' ')
p = re.compile(
'\n{2,}') #replace more than 2 newlines in a row into one newline
htmls = p.sub('\n', htmls)
newdoc = html.document_fromstring(htmls)
return newdoc.text_content()