def repost_timeline(self, client, fid, limit):
mid = misc.decode62(fid)
fh = open('%s_repost.txt' % fid, 'a')
kwds = {
'id': mid,
'count': 100,
'page': 1,
}
buf = []
#while True:
for _ in xrange(1):
rs = client.api.repost_timeline(**kwds) or list()
print 'page: %s,%s' % (kwds['page'], len(rs))
if not rs and kwds['page'] > limit: break
if not rs:
print 'retry...'
continue
for e in rs:
user = e.user
txt = e.text.encode('utf8', 'ignore')
user._txt = txt
user._ts = int(time.mktime(e.created_at.timetuple())),
user._ct = e.created_at.strftime("%Y-%m-%d %H:%M:%S"),
self._write_user(fh, user)
buf.append(user)
kwds['page'] += 1
time.sleep(3)
fh.close()
fh = open('%s_repost2.txt' % fid, 'w')
skips = set()
buf.reverse()
for user in buf:
if user.id in skips: continue
if '此微博已被删除' in user._txt: continue
skips.add(user.id)
self._write_user(fh, user)
fh.close()
def repost_timeline(self, client, fid, limit):
mid = misc.decode62(fid)
fh = open('%s_repost.txt'%fid , 'a')
kwds = {
'id': mid,
'count': 100,
'page': 1,
}
buf = []
#while True:
for _ in xrange(1):
rs = client.api.repost_timeline(**kwds) or list()
print 'page: %s,%s'%(kwds['page'], len(rs) )
if not rs and kwds['page']>limit: break
if not rs:
print 'retry...'
continue
for e in rs:
user = e.user
txt = e.text.encode('utf8','ignore')
user._txt = txt
user._ts = int(time.mktime(e.created_at.timetuple())),
user._ct = e.created_at.strftime("%Y-%m-%d %H:%M:%S"),
self._write_user(fh, user)
buf.append( user )
kwds['page'] +=1
time.sleep(3)
fh.close()
fh = open('%s_repost2.txt'%fid , 'w')
skips =set()
buf.reverse()
for user in buf:
if user.id in skips: continue
if '此微博已被删除' in user._txt: continue
skips.add( user.id )
self._write_user( fh, user )
fh.close()
def repost2_timeline(self, client, fid, limit):
mid = misc.decode62(fid)
#fh = open('%s_repost2.txt'%fid , 'a')
fh = open('%s_repost2.txt' % fid, 'w')
kwds = {
'id': mid,
'count': 100,
'page': 1,
}
iRetry = 0
while True:
time.sleep(5)
rs = client.api.repost_timeline(**kwds) or list()
print 'page: %s,%s' % (kwds['page'], len(rs))
if not rs and kwds['page'] > limit: break
if not rs:
print 'retry...'
iRetry += 1
if iRetry > 3: break
continue
iRetry = 0
print '... find %s' % len(rs)
for e in rs:
txt = e.text.encode('utf8', 'ignore'),
#if not '@屈臣氏中国' in txt: continue
#user = e.user
obj = {
'mid': e.mid,
'txt': e.text.encode('utf8', 'ignore'),
'ts': int(time.mktime(e.created_at.timetuple())),
'ca': e.created_at.strftime("%Y-%m-%d %H:%M:%S"),
'user_name': e.user.screen_name.encode('utf8', 'ignore'),
'user_id': e.user.id,
}
fh.write('%s\n' % json.dumps(obj))
fh.flush()
kwds['page'] += 1
fh.close()
def repost2_timeline(self, client, fid, limit):
mid = misc.decode62(fid)
#fh = open('%s_repost2.txt'%fid , 'a')
fh = open('%s_repost2.txt'%fid ,'w' )
kwds = {
'id': mid,
'count': 100,
'page': 1,
}
iRetry = 0
while True:
time.sleep(5)
rs = client.api.repost_timeline(**kwds) or list()
print 'page: %s,%s'%(kwds['page'], len(rs) )
if not rs and kwds['page']>limit: break
if not rs:
print 'retry...'
iRetry +=1
if iRetry>3: break
continue
iRetry = 0
print '... find %s'%len(rs)
for e in rs:
txt = e.text.encode('utf8','ignore'),
#if not '@屈臣氏中国' in txt: continue
#user = e.user
obj = {
'mid': e.mid,
'txt': e.text.encode('utf8','ignore'),
'ts': int(time.mktime(e.created_at.timetuple())),
'ca': e.created_at.strftime("%Y-%m-%d %H:%M:%S"),
'user_name': e.user.screen_name.encode('utf8','ignore'),
'user_id': e.user.id,
}
fh.write('%s\n'%json.dumps(obj))
fh.flush()
kwds['page'] +=1
fh.close()
