page_src = waitVisible('.sfdc_richtext').get_attribute('innerHTML')
h = html2text.HTML2Text()
h.ignore_emphasis=True # don't add '*' surrounding word
h.body_width=0 # don't wrap long line
artTxt = h.handle(page_src)

def guessVersion(txt:str)->str:
    m=re.search(r'version:\s*(\d+[\.\d]*)', txt, re.I)
    if m:
        return m.group(1)
    else:
        return None


def guessFileSize(txt:str)->int:
    m = re.search(r'size:\s*(\d+\.?\d+?)\s*(KB|MB)', txt, re.I)
    if m:
        unitDic=dict(KB=1024,MB=1024*1024)
        return int(float(m.group(1)) * unitDic[m.group(2).upper()])
    else:
        return None


def guessDate(txt:str) -> datetime:
    m = re.search(r'\d{1,2}/\d{1,2}/\d{4}', txt)
    if m:
        return datetime.strptime(m.group(0), '%m/%d/%Y')
    else:
        return None


def getSizeDateVersion(txt:str, ithDownload:int)->(int,datetime,str,str):
    lines = txt.splitlines()
    def getLineIdx():
        numDownloads=0
        for lineIdx,line in enumerate(lines):
            if '[Download]' in line:
                if numDownloads == ithDownload:
                    return lineIdx
                numDownloads+=1
        return -1
    lineIdx=getLineIdx()
    if lineIdx==-1:
        raise StopIteration('ithDownload=%d'%ithDownload)
    fileSize,relDate,version=None,None,None
    downUrl=None
    for idx,line in enumerate(lines[lineIdx::-1]):
        line = line
        if '[Download]'in line:
            if idx>0:
                break
            if not downUrl:
                downUrl=re.search(r'\[Download\]\((.+?)\)',line).group(1)
        if not fileSize:
            fileSize = guessFileSize(line)
        if not relDate:
            relDate = guessDate(line)
        if not version:
            version = guessVersion(line)
        if fileSize is not None and relDate is not None and version is not None:
            return fileSize,relDate,version,downUrl
    return fileSize,relDate,version,downUrl