def xml_fmt_convert(html):
soup = bs4.BeautifulSoup(html)
# remove tag and its contents
soup = remove_tag(soup, ['pre'])
# remove tag, leave its contents
soup = unwrap_tag(soup, ['br', 'span'])
# rename tag: div -> p
for i in soup.find_all('div'):
i.name = 'p'
# deal with the 'style' attributes in <img>
tag_img = soup.find_all('img')
for i in tag_img:
try:
couple = get_style_couple(i['style'].replace('px', ''))
for attr, val in couple:
i[attr] = val
del i['style']
except KeyError:
pass
#soup_fmt = soup.prettify(formatter=None)
soup_fmt = replaceCharEntity(str(soup))
soup_fmt = '<body>' + soup_fmt + '</body>'
# convert <img.../> tag into <img...></img>
soup_fmt = soup_fmt.replace('/>', '>')
soup_fmt = re.sub('<img[^>]+>', lambda x: x.group() + '</img>', soup_fmt)
return soup_fmt.replace('\r', '').replace('\n', '')
def getCatArticle(cat_id=None):
if not cat_id:
return ''
pattern = re.compile(r"<p>img\d+\</p>")
con = '<body>'
for ar in NewArticle.objects.filter(cat=cat_id):
con += pattern.sub(find_img, replaceCharEntity(ar.content))
con += '</body>'
return re.sub("\r\n", '', con)
def getCatArticle(cat_id=None):
if not cat_id:
return ''
pattern = re.compile(r"<p>img\d+\</p>")
con='<body>'
for ar in NewArticle.objects.filter(cat=cat_id):
con+=pattern.sub(find_img,replaceCharEntity(ar.content) )
con+='</body>'
return re.sub("\r\n",'',con)
def test_xml(id):
event = {}
ca = NewAppEvent(None,id)
cont = ca['event_content'][0][1]
cont = cont.replace('\n', '').replace('\r', '').replace('\r\n', '')
event['mobileU'] = cont
soup = BeautifulSoup(cont)
# remove tag and its contents
soup = unwrap_tag(soup, ['br', 'span','pre'])
# rename tag: div -> p
for i in soup.find_all('div'):
i.name = 'p'
# deal with the 'style' attributes in <img>
tag_img = soup.find_all('img')
for i in tag_img:
try:
couple = get_style_couple(i['style'].replace('px', ''))
for attr, val in couple:
i[attr] = val
del i['style']
except KeyError:
pass
#soup_fmt = soup.prettify(formatter=None)
#soup_fmt = replaceCharEntity(str(soup))
#pattern = re.compile(r"<p>img\d+\</p>")
#soup=replaceCharEntity(str(soup))
#soup_fmt = re.sub(ur"<p>img\d+\</p>" , find_img, soup )
#try:
soup_fmt = re.sub(ur"<p>img\d+\</p>" , find_img,replaceCharEntity(str(soup)) )
#except:
# soup_fmt =replaceCharEntity(str(soup))
soup_fmt = '<body>' + soup_fmt + '</body>'
# convert <img.../> tag into <img...></img>
soup_fmt = soup_fmt.replace('/>', '></img>')
#soup_fmt = re.sub('<img[^>]+>', lambda x: x.group() + '</img>', soup_fmt)
event['mobileURL'] = soup_fmt.replace('\r', '').replace('\n', '')
return event
def gettext(strings=None):
if not strings:
return ''
pattern = re.compile(r"<p>img\d+\</p>")
con='<body>'
con+=pattern.sub(find_img,replaceCharEntity(strings) )
con+='</body>'
# add quote before and after the attributes
pattern = re.compile("(?P<pre>\w+=)(?P<post>\"?[^ \f\n\r\t\v<>]+\"?)")
con = re.sub(pattern, add_quote, con)
con = re.sub(r":(\S+);",r'="\1"', con)
return re.sub("\r\n",'',con)
def gettext(strings=None):
if not strings:
return ''
#pattern = re.compile(r"<p>img\d+\</p>")
#con='<body>'
con = re.sub(r"<p>img\d+\</p>", find_img, replaceCharEntity(strings))
#con+='</body>'
# add quote before and after the attributes
#pattern = re.compile("(?P<pre>\w+=)(?P<post>\"?[^ \f\n\r\t\v<>]+\"?)")
#con = re.sub(pattern, add_quote, con)
#con = re.sub(r":(\S+);",r'="\1"', con)
return con
def str_html(strs=None):
strs = strs.replace(' ','').replace('\r','').replace('\n','').replace('<p>','').replace('</p>','\r\n').replace('<br>','\r\n')\
.replace('<br/>','\r\n').replace('<br />','\r\n').replace('\r\n\r\n','\r\n')
strs = replaceCharEntity(strs)
return strs
def str_html(str=None):
str = str.replace(' ','').replace('\r','').replace('\n','').replace('<p>','').replace('</p>','\r\n').replace('<br>','\r\n')\
.replace('<br/>','\r\n').replace('<br />','\r\n').replace('\r\n\r\n','\r\n')
str = replaceCharEntity(str)
return str