import DGStorage as DGS
a = DGS.DGStorage()
a.select('biology')
ok = False
i = 0
while ok == False:
res = a.fetch(20, (i - 1) * 20)
i += 1
if len(res) == 0:
ok = True
for item in res:
a.setprop(item["uid"], "printed", "no")
print('set ' + item["prop"]["name"])
import DGStorage as DGS;
dbhandle=DGS.DGStorage();
dbhandle.create("/var/lib/bipt");
import DGStorage as DGS
dbHandle = DGS.DGStorage()
dbHandle.select("/var/lib/bipt")
dbHandle.add(
"5120150743", "宋亚意", {
"name": "宋亚意",
"id": 5120150743,
"music": "Whistle",
"praise": 0,
"pic": None,
"phone": "?!?",
"description": "来自计153班"
})
import DGStorage as DG
import subprocess;
import os;
import time;
a=DG.DGStorage()
def checkout(web):
subprocess.check_output('wget --user-agent="Links (2.8; Linux 2.6.32-504.30.3.el6.x86_64 x86_64; GNU C 4.4.7; text)" --output-document=tmp -q "'+str(web)+'"',shell=True);
a.create('yuwenpoint')
a.select('yuwenpoint')
i=1;
while i<=184:
checkout('http://www.mofangge.com/qlist/yuwen/'+str(i));
print(i);
with open('tmp') as cont:
a.add(i,cont.read());
i+=1;
os.remove('tmp');
time.sleep(3);
print('done');
b=DG.DGStorage()
b.create('yingyupoint')
b.select('yingyupoint')
i=1;
while i<=333:
checkout('http://www.mofangge.com/qlist/yingyu/'+str(i));
print(i);
with open('tmp') as cont:
b.add(i,cont.read());
i+=1;
os.remove('tmp');
import DGStorage as D
a=D.DGStorage()
a.select('swpoint');
a.zip('biology');
import DGStorage as DG;
import urllib.parse;
a=DG.DGStorage();
type='biology';
a.select(type);
b=DG.DGStorage();
b.select('knowledgebase');
ok=False;
i=0;
while ok==False:
res=a.fetch(20,(i-1)*20);
i+=1;
if len(res)==0:
ok=True;
content=[];
for item in res:
split=item["content"].split('\n');
split=split[38].split('●');
#print(len(split));
if len(split)==31: #超过一页了，最后一项是分页
split=split[1:-1];
split=split[0:4]; #要不然题太多了
for element in split:
element=element.split('</a>')[0];
#print(element.find('.html">'));
url=element[element.find('<a href=')+9:element.find('.html">')+5];
element=element[element.find('.html">')+7:element.find('</a>')-1];
#print(element);
content.append(element);
b.add(url,'',{"content":element,"type":type,"kbname":item["prop"]["name"],"kb":item["uid"]});
print('add '+item["uid"]);
from pyfetch import *
import DGStorage as DG
import time
import urllib.parse
import os
a = DG.DGStorage()
a.select('knowledgebase')
ok = False
i = 199
while ok == False:
res = a.fetch(20, (i - 1) * 20)
i += 1
if i == 399:
ok = True
if len(res) == 0:
ok = True
for item in res:
fetch(urllib.parse.unquote_plus(item["key"]), 'tmp')
with open('tmp') as cont:
a.put(item["uid"], cont.read())
os.remove('tmp')
print('put cont ' + item["uid"])
time.sleep(3)
print('DONE==================================================')