ct=[] for h in div.findAll(["h2","h3","h4","h5","h6"]): c=int(h.name[1]) aux=[x for x in ct if x<c] if len(aux)>0: a=aux[-1]+1 if a<c: flag=True h.name="h"+str(a) ct.append(c) if flag: fix_h(div) oht="out/tecmint.html" out = util.get_tpt("LFCS and LFCE by tecmint.com","rec/tecmint.css") h1=out.new_tag("h1") h1.string="LFCS" out.body.div.append(h1) index=True flag=0 part=re.compile(u"\s*[\-–—]\s*Part\s+\w+$", re.UNICODE | re.IGNORECASE) for url in urls: if not url.startswith("http"): hr=out.new_tag("div") hr.attrs["class"]="h0" hr.string=url out.body.div.append(hr) continue
def set_anchor(i,ca): a=soup.new_tag("a", **{"href": "#"+i.attrs['id'], "title":u"Cápitulo "+str(ca)}) if i.name=="fieldset": i=i.legend a.string=i.string i.string="" i.attrs["class"]="item" i.append(a) def get_lab(f,txt): a=soup.new_tag("a", **{"href": "labs/"+f, "title":"Fichero original en: https://lms.360training.com/custom/12396/808239/"+f}) a.string=txt return a soup = util.get_tpt("LFS201","rec/lfs201.css") fldB=None divCp=None hts=sorted(glob.glob('html/clean/*.html')) for ht in hts: soup2 = util.get_soup(ht) t=soup2.title b=soup2.body if "_popup" in ht: n=3 else: ca=int(cp.sub("\\1",ht)) if ca>caB: