def add_user(self, num = 10000):
s = 0
if os.path.isfile(self.user_line):
with file(self.user_line, 'r')as f:
r = f.read().strip()
try:
s = int(r)
except ValueError:
s = 0
users = csdn().query_user(s=s, e=num)
print '一共 %s 个21cn.com 帐号' % len(users)
#{'user':'******', 'pwd':'password', 'doubanname':'douban name'}
for index, i in enumerate(users):
dban = douban()
print "尝试帐号：[ %s/%s | %s ] %s -- %s" %(index, len(users), i.get('id'), i.get('email').encode('utf8'), i.get('pwd').encode('utf8'))
if dban.login(i.get('email').encode('utf8'), i.get('pwd').encode('utf8'), tuser=True):
user = {'user':dban.user, 'pwd':dban.pwd, 'doubanname':dban.doubanname.decode('utf8').encode('utf8')}
douban_db().add_user(user)
dban.logout()
with file(self.user_line, 'w')as f:
f.write(str(int(i.get('id'))))
#self.check403()
print ''
print "==" * 40
print ''
def say(self, tid='54885639'):
# http://www.douban.com/group/topic/54885639/?start=99999#last
if not tid :
print '帖子ID不正确.'
return False
url = 'http://www.douban.com/group/topic/%s/?start=99999999999#last' % tid
con = str(self.req(url))
if con == '403':
print '非公开小组：http://www.douban.com/group/topic/%s/' % tid
return False
if con == '404':
print '帖子不存在：http://www.douban.com/group/topic/%s/' % tid
return False
if con.find('只有小组成员才能发言') > 200:
#group_name = re.findall('group-item.+?<a href="(.+?)".+?>', con, re.S)
group_name = re.findall('group-item.+?<a href=".+?group/(.+?)/\?.+?".+?>', con, re.S)
if len(group_name) > 0:
group_name = group_name[0]
if not self.join_group(group_name):
return False
con = str(self.req(url))
else:
print '帖子找不到小组：http://www.douban.com/group/topic/%s/' % tid
elif con.find('你已经申请加入小组，请等待小组管理员审核') > 200:
print '你已经申请加入小组，请等待小组管理员审核'
return False
data = self.getfrom(con, 1)
del data['sync_to_mb']
list_say = self.choice_say(1, tid=tid)
data['rv_comment'] = choice(list_say)
url = 'http://www.douban.com/group/topic/%s/add_comment#last' % tid
con = str(self.req(url, 'POST', data = data))
i_say = self.get_i_say(con)
data = {}
#{'user_id': '1', 'cid':'say id', 'tid':'topic id', 'con': 'say what', 'rtime': '2014-07-31 18:33:00', 'state':1}
data['user_id'] = douban_db().query_user(self.user)[0].get('id')
data['cid'] = i_say[1]
data['tid'] = tid
data['con'] = i_say[0]
data['rtime'] = i_say[3]
data['state'] = '1'
if not i_say:
print '评论失败：[http://www.douban.com/group/topic/%s/]' % tid
data['state'] = '0'
douban_db().add_say(data)
return False
print '%s>评论内容保存在数据库，%s 行受影响' % ('-' * 150, douban_db().add_say(data))
return True
def add_topic(self, tid):
"""{'user':'******', 'tid':'57533625', 'title':'标题1', 'con':'内容', 'group':'buybook', 'ctime':'2014-07-30 10:42:52', 'atime':'2014-07-31 16:29:05' }"""
if not tid:
return None
con = str(self.req('http://www.douban.com/group/topic/%s/' % tid))
data = {'tid': tid}
data['group'] = re.findall('group-item.+?<a href=".+?group/(.+?)/\?.+?".+?>', con, re.S)[0].decode('utf8')
data['title'] = [i.strip() for i in re.findall('<h1>(.+?)</h1>', con, re.S)][0].decode('utf8')
data['user'], data['ctime'] = [i.decode('utf8') for i in re.findall('topic-doc.+?来自: .+?>(.+?)</a.+?color-green">(.+?)</span', con, re.S)[0]]
data['con'] = BeautifulSoup(re.findall('(<div id="link-report".+?)<div class="sns-bar"', con, re.S)[0]).text.strip().encode('utf8').decode('utf8')
data['atime'] = str(datetime.datetime.now())
return douban_db().add_topic(data)
def db(self):
return mdb.douban_db()
def get_new_says(self, sid):
info = douban_db().get_new_say(sid)
if len(info) > 0:
return info[0]
else:return {}
def get_topic(self):
return douban_db().get_topic()
def query_user(self, user=""):
self.users = douban_db().query_user(user)
return self.users
def del_user(self, user):
if self.tuser: return None
print "删除帐号:%s" % user
return douban_db().del_user(user)
def alt_user(self, user):
if self.tuser: return None
print "%s 被禁用. 删除该帐号" % user
return douban_db().alt_user(user)