def web_getXTxt100(df,rs0,txtn0=200):
for i, row in df.iterrows():
uss,hdr,txt=row['url'],row['hdr'],''
hdr = re.sub('[\\\/:*?"<>|]','-',hdr)
if len(uss)>20:txt=web_getXTxt010x9(uss);#print('h2,',chdr)
#
if len(txt)>txtn0:
rss=rs0
if not os.path.exists(rss):os.mkdir(rss)
#
fss=rss+hdr+'.txt';print(' ',fss)
css=hdr+'\n'+uss+'\n\n'+txt
#print(css,'\n',fss)
zt.f_add(fss,css,True)
def web_get001txt(url,ucod='gb18030',ftg='',fcod='gbk'):
htm,rx='',web_get001(url)
if rx!=None:
xcod=rx.apparent_encoding;#print(xcod,uss)
rx.encoding =xcod #gb-18030
#dss=rx.text
htm=rx.text;#print(htm)
if xcod.upper()=='UTF-8':
#print('@@u8a');#print(htm)
htm=htm.replace(' ',' ')
css = htm.encode("UTF-8",'ignore').decode("UTF-8",'ignore')
css=css.replace(u'\xfffd ', u' ')
css=css.replace(u'\xa0 ', u' ')
htm = css.encode("GBK",'ignore').decode("GBK",'ignore')
#
if ftg!='':zt.f_add(ftg,htm,True,cod=fcod)
#
return htm