for i in range(my_range):
cousor=cnx.cursor()
sql_sentense="select * from url_content where place>=%s and place <%s" # place为id
sql_stentese2="update url_content set flag1=3, attach_url=%s,content=%s where place =%s"
#atturl为附件url所在的新字段，content为内容字段
cousor.execute(sql_sentense,(x,x+m))
str=''
list1=[]
for content in cousor.fetchall():
atturl_list=[]
all_couple=[]
str1=content[3]
con_url=content[2]
con_id=content[0]
text = attatch_url(str1,con_url)
str2=text.Replace_Char(str1)
pre_url=text.get_url(str2)
for i in pre_url:
a=text.combin_url(text.get_domain(con_url,text.has_http(i)),i)
atturl_list.append(a)
all_couple.append((i,a))
for i in all_couple:
str2=str2.replace(i[0],i[1])
if atturl_list:
print [atturl_list,con_id]
encodedjson = json.dumps(atturl_list)
list1.append((encodedjson,str2,con_id))
for i in range(my_range):
t6=time.time()
cursor=cnx.cursor()
sql_sentense="select * from url_content where place>=%s and place <%s"
sql_sentense2='update url_content set flag1=1, attach_url=%s where place =%s'
cursor.execute(sql_sentense,(x,x+m))
list1=[]
str=''
for content in cursor.fetchall():
# str='''<a href="/InvestmentInfo/ZhaoBiao/InviteNoticeDetail.aspx?id=127814">[email protected]<'''
str=content[3]
# url1=content[2]
# print url1.encode('GBK','ignore')
att_url=content[2]
text = attatch_url(str,att_url)
url=text.get_attatch_url()
con_id=content[0]
if url != []:
encodedjson = json.dumps(url)
list1.append((encodedjson,con_id))
else:
list1.append((('',con_id)))
# print list1
tuple_in=tuple(list1)
# print tuple_in
print x
cursor.close()
cursor2=cnx.cursor()
cursor2.executemany(sql_sentense2,tuple_in)
cnx.commit()
