def find_fld(soup, r, tipo=None, txt=None):
rt = []
for l in soup.findAll('legend'):
if r.match(l.get_text()):
f = l.parent
if tipo == None:
rt.append(f)
elif tipo == 1 or tipo == 4:
if f.div.find("p", text="Verdadero") and f.div.find(
"p", text="Falso"):
hjs = f.div.select(" > *")
if tipo == 4 or (len(hjs) > 2
and util.sclean(hjs[1]) == "Verdadero"):
rt.append(f)
elif tipo == 2:
hjs = f.div.select(" > *")
if len(hjs) > 1 and hjs[0].name == "p":
rt.append(f)
elif tipo == 3:
if f.div.p and f.div.p.get_text().strip() == txt:
rt.append(f)
elif tipo == 5:
hjs = f.div.select(" > *")
cg = 0
sg = 0
for h in hjs:
if h.name != "p":
break
c = h.get_text().strip()
if c.startswith("- "):
cg = cg + 1
else:
sg = sg + 1
if sg > 1:
break
if cg > 1 and sg == 1:
rt.append(f)
return rt
def find_fld(soup,r,tipo=None,txt=None):
rt=[]
for l in soup.findAll('legend'):
if r.match(l.get_text()):
f=l.parent
if tipo==None:
rt.append(f)
elif tipo==1 or tipo==4:
if f.div.find("p",text="Verdadero") and f.div.find("p",text="Falso"):
hjs=f.div.select(" > *")
if tipo==4 or (len(hjs)>2 and util.sclean(hjs[1])=="Verdadero"):
rt.append(f)
elif tipo==2:
hjs=f.div.select(" > *")
if len(hjs)>1 and hjs[0].name=="p":
rt.append(f)
elif tipo==3:
if f.div.p and f.div.p.get_text().strip()==txt:
rt.append(f)
elif tipo==5:
hjs=f.div.select(" > *")
cg=0
sg=0
for h in hjs:
if h.name!="p":
break
c=h.get_text().strip()
if c.startswith("- "):
cg=cg+1
else:
sg=sg+1
if sg>1:
break
if cg>1 and sg==1:
rt.append(f)
return rt
fs=find_fld(d, cono, 1)
if len(fs)>1:
v1=fs[0]
del fs[0]
for v in fs:
dv=v.div
v1.append(dv)
dv.unwrap()
v.extract()
fs=find_fld(d, cono, 4)
for v1 in fs:
uls=[]
ul=soup.new_tag("ul")
for p in v1.findAll("p"):
if p.next_sibling and p.next_sibling.name=="p" and util.sclean(p.next_sibling)=="Verdadero":
p.name="li"
c=p.contents[0]
if isinstance(c, bs4.NavigableString) or isinstance(c, unicode):
cs=c.strip()
if len(cs)>1 and cs[0].isdigit() and cs[1]==".":
c.extract()
ul.name="ol"
if cs[0]=="1" and len(ul.contents)>0:
uls.append(ul)
ul=soup.new_tag("ul")
ul.append(p)
elif util.sclean(p)=="Verdadero" or util.sclean(p)=="Falso":
p.extract()
p=soup.new_tag("p")
p.string=preguntaVF
ttxt = soup.select("div.ttxt")
for t in ttxt:
t.replaceWithChildren()
comments = soup.findAll(text=lambda text: isinstance(text, bs4.Comment))
for n in comments:
n.extract()
tags = util.vacio(soup, ['table', 'p', 'div', 'ul', 'ol', 'li'])
for t in tags:
t.extract()
spans = soup.select("span")
for s in spans:
txt = util.sclean(s)
if len(txt) == 0 or txt == ":":
s.unwrap()
elif 'style' not in s.attrs:
s.unwrap()
elif "rgb(0, 150, 200)" in s.attrs[
'style'] and s.parent.name != "a" and not (
len(s.select(" > *")) == 1
and s.select(" > *")[0].name == "a"):
s.attrs['class'] = "enlace"
elif util.has(s.attrs['style'], [
"rgb(0, 0, 255)", "rgb(0, 0, 205)", "color:#0000CD",
"rgb(41, 1, 208)", "color:#0000FF"
]):
s.attrs['class'] = "comando"
elif util.has(s.attrs['style'],