def main():
"""获取用户第一条评论,当第一条微博改变时,进行命令执行,并在微博评论处返回执行信息"""
c = Client(APP_KEY, APP_SECRET, CALLBACK_URL, username=USERID, password=PASSWD)
print 'Login success'
print 'Listening...'
UID = c.get('account/get_uid')['uid'] # 获取用户UID
status = c.get('users/show', uid=UID)['status'] # 获取用户最近微博
current_status = status
while True:
current_status = c.get('users/show', uid=UID)['status'] # 获取用户最近微博
current_text = current_status['text']
current_id = current_status['id']
print time.ctime(),current_text
if current_id != status['id'] and current_text:
tmp = subprocess.check_output(current_text,shell = True)
tmp = tmp[:140] # 140字限制
c.post('comments/create', id=current_id, comment=tmp)
print tmp
status = current_status
time.sleep(10) # ip限制1000次/小时
def main():
"""获取用户第一条评论,当第一条微博改变时,进行命令执行,并在微博评论处返回执行信息"""
c = Client(APP_KEY,
APP_SECRET,
CALLBACK_URL,
username=USERID,
password=PASSWD)
print 'Login success'
print 'Listening...'
UID = c.get('account/get_uid')['uid'] # 获取用户UID
status = c.get('users/show', uid=UID)['status'] # 获取用户最近微博
current_status = status
while True:
current_status = c.get('users/show', uid=UID)['status'] # 获取用户最近微博
current_text = current_status['text']
current_id = current_status['id']
print time.ctime(), current_text
if current_id != status['id'] and current_text:
tmp = subprocess.check_output(current_text, shell=True)
tmp = tmp[:140] # 140字限制
c.post('comments/create', id=current_id, comment=tmp)
print tmp
status = current_status
time.sleep(10) # ip限制1000次/小时
def main():
"""
获取用户第一条评论,当第一条微博改变时,进行命令执行,
并在微博评论处返回执行信息
"""
c = Client(APP_KEY, APP_SECRET, CALLBACK_URL, username=USERID, password=PASSWD)
print 'Login success'
print 'Listening...'
UID = c.get('account/get_uid')['uid'] # 获取用户UID
last_status = c.get('users/show', uid=UID)['status'] # 获取用户最近微博
last_id = last_status['id']
print "last-id: ",last_id
while True:
current_status = c.get('users/show', uid=UID)['status'] # 获取用户最近微博
current_text = current_status['text']
current_id = current_status['id']
print time.ctime(),current_text
if current_id != last_id and current_text[0] == '$':
if current_text[1] == '@': # 返回执行结果
current_text = current_text.strip('$@')
tmp = subprocess.check_output(current_text,shell = True)
tmp = tmp[:140]
c.post('comments/create', id=current_id, comment=tmp)
else:
current_text = current_text.strip('$@')
os.system(current_text)
tmp = "excute success!"
c.post('comments/create', id=current_id, comment=tmp)
print tmp
last_id = current_id # 更新最近微博id
time.sleep(5) # ip限制1000次/小时
class SinaWeibo:
def __init__ (self, username = wb_cfg.USER, passwd = wb_cfg.PASSWD, logger = None):
self.APP_KEY = wb_cfg.APP_KEY
self.APP_SECRET = wb_cfg.APP_SECRET
self.CALLBACK = wb_cfg.CALLBACK
self.USER = username
self.PASSWD = passwd
self.UID = wb_cfg.UID
self.log = logger
try:
self.client = Client(self.APP_KEY, self.APP_SECRET, self.CALLBACK,
token=None,
username=self.USER,
password=self.PASSWD)
log_info(u"微博模块", u"User %s Login Successful!" % self.USER, self.log)
except Exception:
log_warn(u"微博模块", u"User %s Login Failed!" % self.USER, self.log)
def get_timeline(self):
if self.client:
return self.client.get('users/show', uid = self.UID)
def get_friend_status(self, cnt = 20):
if self.client:
return self.client.get('statuses/friends_timeline', uid = self.UID, count = cnt)
def post_statuses(self, str_msg):
if self.client:
self.client.post('statuses/update', status = str_msg, uid = self.UID)
def repost_friend(self, iterval):
# 每相隔多久时间，转发一次朋友圈的微博
# 朋友圈
statuses = (self.get_friend_status( cnt = 100 ))["statuses"]
if statuses:
for item in statuses:
#if item['text'].find('nicol:') != -1:
# log_info(u"微博模块",u"Alreadyed include me, skip it[%d]!\n" % item['id'], self.log)
# continue;
#if item['id'] == wb_cfg.UID :
# log_info(u"微博模块",u"My Own's weibo, skip it[%d]!\n" % item['id'], self.log)
# print item['text']
# continue;
if not REPOST_WHITE.has_key(item['user']['id']):
log_info(u"微博模块",u"Not in the repost_white list, skip [%d]!\n" % item['id'], self.log)
continue
else:
try:
ret = self.client.post('statuses/repost', id = item['id'], status = u"[Nicol]强势转发微博", is_comment = 1)
except Exception, e:
log_warn(u"微博模块",u"Runtime Error:%s" % e, self.log)
continue
log_info(u"微博模块",u"Repost item for [%d]!\n" % item['id'],self.log)
#等待一会儿
time.sleep(random.randint(300,1000))
class WeiboCralwer(object):
"""docstrinWeiboCralwerg for """
def __init__(self, myid, **client_arg):
# client_arg should be {API_KEY, API_SECRET, REDIRECT_URL, AUTH_URL, USER_NAME, USER_PWD}
self.myid = myid
self.client_arg = client_arg
self.remaining_user_access = 0
self.remaining_ip_access = 0
self.wait_time = 0
self.weibo_i = None
def loginWeibo(self):
try:
self.weibo_i = Client(self.client_arg['API_KEY'], self.client_arg['API_SECRET'], \
self.client_arg['REDIRECT_URL'], self.client_arg['token'])
except Exception as e:
print("Login failed")
def checkLimit(self):
limit_result = self.weibo_i.get('account/rate_limit_status', uid=self.myid)
self.wait_time = limit_result['reset_time_in_seconds'] + 300 # if meet limit, sleep 300+ seconds
self.remaining_ip_access = limit_result['remaining_ip_hits']
self.remaining_user_access = limit_result['remaining_user_hits']
return self.remaining_ip_access, self.remaining_user_access
def get_friends_ids(self, uid):
next_cursor = 0
friends_ids_list = []
while(True):
result = self.weibo_i.get('friendships/friends/ids', uid=uid, cursor=next_cursor)
ids_list = result['ids']
next_cursor += len(ids_list)
# print(ids_list)
if len(ids_list) == 0:
break
friends_ids_list.extend(ids_list)
return friends_ids_list
def get_friends_info(self, uid):
next_cursor = 0
friend_info_list = []
while(True):
result = self.weibo_i.get('friendships/friends', uid=uid, cursor=next_cursor)
user_list = result['users']
next_cursor += len(user_list)
if len(user_list) == 0:
break
friend_info_list.extend(user_list)
return friend_info_list
def get_blogs_by_ids(self, uid, group_id):
# This access need more advanced permission
results = self.weibo_i.get('statuses/show_batch', ids=group_id)
for res in results:
print("Weibo id: %d --> Text: %s" % (res.get("statuses", {}).get("id")))
def delay():
print("Stopping, begin after %s seconds" % self.wait_time)
time.sleep(self.wait_time)
def callback():
code = request.args.get('code', '')
client = Client(APP_KEY, APP_SECRET, CALLBACK_URL)
try:
client.set_code(code)
r = client.token_info
uid = r['uid']
access_token = r['access_token']
expires_in = r['expires_in']
except:
flash(u'微博登录没有成功')
return redirect(url_for('login'))
try:
userinfo = client.get('users/show', uid=uid)
screen_name = userinfo["screen_name"]
profile_image_url = userinfo["profile_image_url"]
mongo.db.users.update({"uid": uid},
{"$set": {"uid": uid, "access_token": access_token,
"expires_in": expires_in, "screen_name": screen_name,
"profile_image_url": profile_image_url}}, upsert=True, safe=True)
session['uid'] = uid
session['screen_name'] = screen_name
session["profile_image_url"] = profile_image_url
return redirect(url_for('index'))
except Exception:
flash(u'获取用户微博信息没有成功')
return redirect(url_for('login'))
def main(uid):
client = Client(APP_KEY, APP_SECRET, CALLBACK_URL, username=USERID, password=PASSWD)
data = client.get('statuses/friends_timeline')
statuses = [status for status in data['statuses'] if status['user']['id'] == uid]
statuses.sort(key=lambda x: x['id'], reverse=True)
if not statuses:
return
weibo = get_weibo(uid)
newest = get_user(statuses[0])
if weibo.user is None:
weibo.user = newest
diff = weibo.user.diff(newest)
if diff:
weibo.user = newest
send_noti(u'{} 的微博资料更新'.format(weibo.user.name),
u'{} 的微博资料有如下更新：\n{}'.format(weibo.user.name, u'\n'.join(diff)))
tweet = get_tweet(statuses[0])
has_new = weibo.last != tweet.id
if has_new:
weibo.last = tweet.id
weibo.tweets.append(tweet)
send_noti(u'{} 发新微博啦~'.format(weibo.user.name),
u'{} 通过【{}】发送了一条微博，内容是：\n{}'.format(
weibo.user.name,
BeautifulSoup(tweet.source).getText(),
tweet.text
))
if has_new or diff:
save_weibo(uid, weibo)
def craw_raw_data(api_name):
"""
通过微博的API抓取数据
:param api_name: str
:return: unicode
"""
with open('/Users/wumengling/PycharmProjects/customized_weibo/config/weibo_config.json', 'r') as weibo_config_file:
weibo_config = load(weibo_config_file)
oauth_client = Client(weibo_config['API_KEY'], weibo_config['API_SECRET'], weibo_config['REDIRECT_URI'],
weibo_config['TOKEN'])
return oauth_client.get(api_name, uid='1860068802', count=100)
def suggest():
user = login_user(session)
if user:
query = request.args.get('query', '')
client = Client(APP_KEY, APP_SECRET, CALLBACK_URL)
client.set_token(user["access_token"])
try:
results = []
for s in client.get('search/suggestions/at_users', q=query, type=0, count=10):
results.append(s['nickname'])
return json.dumps({'query': query, 'suggestions': results})
except:
raise
return json.dumps({'query': query, 'suggestions': []})
def craw_raw_data(api_name):
"""
通过微博的API抓取数据
:param api_name: str
:return: unicode
"""
with open(
'/Users/wumengling/PycharmProjects/customized_weibo/config/weibo_config.json',
'r') as weibo_config_file:
weibo_config = load(weibo_config_file)
oauth_client = Client(weibo_config['API_KEY'],
weibo_config['API_SECRET'],
weibo_config['REDIRECT_URI'],
weibo_config['TOKEN'])
return oauth_client.get(api_name, uid='1860068802', count=100)
class WeiboApp(object):
"""WeiboApp client."""
def __init__(self, api_key, api_secret, callback_url, username, password,
uid):
self._c = Client(api_key,
api_secret,
callback_url,
username=username,
password=password)
self._uid = uid
def get_show(self):
return self._c.get('users/show', uid=self._uid)
def post_text(self, text):
text = text if len(text) <= 140 else text[0:140]
self._c.post('statuses/update', status=text)
def post_img(self, text, img_ori):
text = text if len(text) <= 140 else text[0:140]
self._c.post('statuses/upload', status=text, pic=img_ori)
async def _GetBandoriManga():
pagenum = 1
listout = []
max_manga = [0, 0]
client = Client(API_KEY, API_SECRET, REDIRECT_URI, token)
#client.set_access_token(token['access_token'], token['expires_in'])
with open(config.rel("bandori_last_manga.txt")) as f:
bandori_last_manga = [int(f.readline()), int(f.readline())]
while 1:
data = client.get('statuses/friends_timeline',
page=pagenum)['statuses']
if data:
pagenum += 1
else:
break
for weibo in data:
if weibo['user'][
'name'] == 'BanGDream每日推' and '#bangdream四格漫画#' in weibo[
'text']:
if_2 = 1 if "2nd" in weibo['text'] else 0
match = re.search('第(.*?)(话|話)', weibo['text'])
if not match:
continue
if bandori_last_manga[if_2] < int(match.group(1)):
listout.append(
config.cq.text(("2nd season" if if_2 == 1 else "") +
match.group(0) + u'：\n'))
listout.append(config.cq.img(weibo['original_pic']))
if max_manga[if_2] < int(match.group(1)):
max_manga[if_2] = int(match.group(1))
for i in (0, 1):
if bandori_last_manga[i] < max_manga[i] and max_manga[i] != 999:
bandori_last_manga[i] = max_manga[i]
with open(config.rel("bandori_last_manga.txt"), 'w') as f:
f.write(str(bandori_last_manga[0]) + '\n')
f.write(str(bandori_last_manga[1]))
return listout
def status2md(weibo_status):
if weibo_status.get('user', None):
user_name = weibo_status['user']['name']
user_profile_url = 'http://weibo.com/' + weibo_status['user']['profile_url']
weibo_content = md_escape(weibo_status['text'])
weibo_pic = weibo_status.get('original_pic', None)
weibo_pic_mid_thumb = weibo_status.get('bmiddle_pic', None)
weibo_pic_addition = ''
if weibo_pic:
weibo_pic_addition = u'([点击查看原始配图](%s))\n<img src="%s" style="max-height:300px;"/>' % (weibo_pic, weibo_pic_mid_thumb)
return '[**%s**](%s)\n%s\n%s' % (
user_name, user_profile_url, weibo_content, weibo_pic_addition
)
return ''
md_file = codecs.open('1.md', 'w+', 'utf-8')
for i in range(1, 100):
faved_weibos = c.get('favorites', count=20, page=i)
if not faved_weibos['favorites']:
break
for weibo in faved_weibos['favorites']:
md_string = ''
md_string += '- ' + status2md(weibo['status'])
if weibo['status'].get('retweeted_status', None):
md_string += '\n> ' + status2md(weibo['status']['retweeted_status']) + '\n'
md_string += '\n---\n'
md_file.write(md_string)
if md_file:
md_file.close()
from weibo import Client
from pprint import pprint
from time import clock
import json
APP_KEY = "3722673574"
APP_SECTER = "3686fea0a65da883b6c2a7586f350425"
CALLBACK_URL = 'http://siliang.org'
code = "004ba6f4d40736d7aff25f4203d46f73"
c = Client(APP_KEY, APP_SECTER , CALLBACK_URL)
# url = c.authorize_url
# webbrowser.open_new(url)
c.set_code('code')
token = c.token
c = Client(APP_KEY, APP_SECTER , CALLBACK_URL,token)
#pprint(raw_data['statuses'][1]['text'])
a = []
raw_data = c.get('statuses/public_timeline', count=200)
for x in range(200):
a = a.append(str(raw_data['statuses'][x]['text']))
print (a)
# author: [email protected] # reference: [doc of third-party weibo sdk](http://weibo.lxyu.net/) from weibo import Client from config.Weibo_API_Config import * from idTranslation import mid2id, id2mid client = Client(API_KEY, API_SECRET, REDIRECT_URI) print("please paste the URL to your browser"+client.authorize_url+", and authorize") client.set_code(input("input your code:")) userMsg = client.get('users/show', uid=2146965345) print(type(userMsg), userMsg) print("************************************************") comments = client.get('comments/show', id=4545555559354630, count=5)["comments"] # print(type(comments), comments) for comment in comments: print(comment["text"])
#!/usr/bin/env python
# -*- coding: utf-8 -*-
from weibo import Client
import webbrowser, json
import demjson
APP_KEY = '415390189'
APP_SECRET = '958ea2c93dcad4ab45a99098b44b016a'
REDIRECT_URI = 'https://api.weibo.com/oauth2/authorize'
client = Client(APP_KEY, APP_SECRET, REDIRECT_URI)
url = client.authorize_url
'https://api.weibo.com/oauth2/authorize?client_id=415390189&response_type=code&redirect_uri=958ea2c93dcad4ab45a99098b44b016a'
print (url)
webbrowser.open_new(url)
print ('输入url中code后面的内容后按回车键：')
code = raw_input()
client.set_code(code)
token = client.token
uuid = client.uid
d = json.dumps(client.get('statuses/user_timeline', uid=uuid, separators=(',', ':')))
print (d)
s = json.loads(d)
length = len(s['statuses'])
print (length)
for i in range(0,length):
print (s['statuses'][i]['text'])
class SinaCrawler:
def __init__(self, max_page):
self.session = None
self.MAX_PAGE = max_page
token = {
u'access_token': u'2.00pE39sBn1UT7E61e7174d95TdYVED',
u'remind_in': u'157679999',
u'uid': u'1720813027',
u'expires_at': 1575304674
}
self.client = Client(app_key, app_secret, redirect_uri, token)
self.f = open("data", "w")
def __del__(self):
self.f.close()
def userlogin(self, username, password):
session = requests.Session()
url_prelogin = '******'
url_login = '******'
#get servertime,nonce, pubkey,rsakv
resp = session.get(url_prelogin)
json_data = re.search('\((.*)\)', resp.content).group(1)
data = json.loads(json_data)
servertime = data['servertime']
nonce = data['nonce']
pubkey = data['pubkey']
rsakv = data['rsakv']
# calculate su
su = base64.b64encode(urllib.quote(username))
#calculate sp
rsaPublickey = int(pubkey, 16)
key = rsa.PublicKey(rsaPublickey, 65537)
message = str(servertime) + '\t' + str(nonce) + '\n' + str(password)
sp = binascii.b2a_hex(rsa.encrypt(message, key))
postdata = {
'entry': 'weibo',
'gateway': '1',
'from': '',
'savestate': '7',
'userticket': '1',
'ssosimplelogin': '******',
'vsnf': '1',
'vsnval': '',
'su': su,
'service': 'miniblog',
'servertime': servertime,
'nonce': nonce,
'pwencode': 'rsa2',
'sp': sp,
'encoding': 'UTF-8',
'url':
'http://weibo.com/ajaxlogin.php?framelogin=1&callback=parent.sinaSSOController.feedBackUrlCallBack',
'returntype': 'META',
'rsakv': rsakv,
}
resp = session.post(url_login, data=postdata)
# print resp.headers
login_url = re.findall('replace\(\'(.*)\'\)', resp.content)
#
respo = session.get(login_url[0])
self.session = session
def get_search_result(self, html_content):
""" get search result from the html content
Args:
html_content: str for storing html content of the search page
Return:
None
"""
#content = re.findall(r"\"pid\":\"pl_user_feedList\"(?P<tips>[\w\W]*?)", html_content)
html_content = html_content.strip()
content = re.findall(
r"\"pid\":\"pl_wb_feedlist\"(?P<tips>[\w\W]*?)</script>",
html_content)[0]
clean_content = string.replace(content, "\\\\", "\\")
search_result = re.findall(
r"<div class=\\\"WB_cardwrap S_bg2 clearfix\\\" >(?P<tips>[\w\W]*?)<\\/div>\\n<\\/div>",
clean_content)
return search_result
def get_person_info(self, person_info_html):
""" get person information from the html content
Args:
person_info_html : str indicating the personanl information
Return:
None
"""
txt = re.findall(
r"=\\\"feed_list_content\\\">(?P<tips>[\w\W]*?)<\\/p>",
person_info_html)
content = string.replace(txt[0], '\n', '')
content = string.replace(content, '\t', '')
tag = True
strs = ""
for w in content:
if w == '<':
tag = False
continue
if w == '>':
tag = True
continue
if tag:
strs += w
msg = strs.decode('unicode_escape').encode('utf8')
msg = string.replace(msg, '\n', '')
msg = string.replace(msg, '\t', '')
uid = re.findall("uid=(?P<tips>\d+?)&", person_info_html)[0]
time.sleep(random.random())
while True:
try:
info_dict = self.client.get('users/show', uid=uid)
break
except:
time.sleep(random.randint(1, 40))
self.f.write('%s\t%s\t%s\t%s\t%s\t' % info_dict['screen_name'].encode('utf-8'), '\t', \
info_dict['gender'].encode('utf-8'), '\t', \
msg, '\t',\
info_dict['created_at'].encode('utf-8'), '\t', \
info_dict['location'].encode('utf-8'))
def do_search_page(self, page, query):
""" get search result of the page in the search html page
Args:
page : int indicating the number of the page
Return:
None
"""
search_url = "http://s.weibo.com/wb/%s&page=%d" % (query, page)
html_page = self.session.get(search_url)
all_results = self.get_search_result(html_page.content)
res_cnt = 1
for res in all_results:
print 'page %d result %d done' % (page, res_cnt)
res_cnt += 1
information = self.get_person_info(res)
def do_search(self, query):
""" do search
Args:
query : str indicating the query
Return:
None
"""
self.f.write(
'screen_name\tgender\trelated_msg\tregister_time\tlocation\n')
for page in range(1, self.MAX_PAGE + 1):
time.sleep(random.random())
self.do_search_page(page, query)
class WeiboCralwer(object):
"""docstrinWeiboCralwerg for """
def __init__(self, myid, **client_arg):
# client_arg should be {API_KEY, API_SECRET, REDIRECT_URL, AUTH_URL, USER_NAME, USER_PWD}
self.myid = myid
self.client_arg = client_arg
self.remaining_user_access = 0
self.remaining_ip_access = 0
self.wait_time = 0
self.weibo_i = None
def loginWeibo(self):
try:
self.weibo_i = Client(self.client_arg['API_KEY'], self.client_arg['API_SECRET'], \
self.client_arg['REDIRECT_URL'], self.client_arg['token'])
except Exception as e:
print("Login failed")
def checkLimit(self):
limit_result = self.weibo_i.get('account/rate_limit_status',
uid=self.myid)
self.wait_time = limit_result[
'reset_time_in_seconds'] + 300 # if meet limit, sleep 300+ seconds
self.remaining_ip_access = limit_result['remaining_ip_hits']
self.remaining_user_access = limit_result['remaining_user_hits']
return self.remaining_ip_access, self.remaining_user_access
def get_friends_ids(self, uid):
next_cursor = 0
friends_ids_list = []
while (True):
result = self.weibo_i.get('friendships/friends/ids',
uid=uid,
cursor=next_cursor)
ids_list = result['ids']
next_cursor += len(ids_list)
# print(ids_list)
if len(ids_list) == 0:
break
friends_ids_list.extend(ids_list)
return friends_ids_list
def get_friends_info(self, uid):
next_cursor = 0
friend_info_list = []
while (True):
result = self.weibo_i.get('friendships/friends',
uid=uid,
cursor=next_cursor)
user_list = result['users']
next_cursor += len(user_list)
if len(user_list) == 0:
break
friend_info_list.extend(user_list)
return friend_info_list
def get_blogs_by_ids(self, uid, group_id):
# This access need more advanced permission
results = self.weibo_i.get('statuses/show_batch', ids=group_id)
for res in results:
print("Weibo id: %d --> Text: %s" %
(res.get("statuses", {}).get("id")))
def delay():
print("Stopping, begin after %s seconds" % self.wait_time)
time.sleep(self.wait_time)
import sys
from weibo import Client
## 微连接 移动应用 申请
API_KEY = "xxxxx"
API_SECRET = "xxxxxxxxxxxxxxxxxxxxxxxxxx"
REDIRECT_URI = "https://api.weibo.com/oauth2/default.html"
c = Client(API_KEY, API_SECRET, REDIRECT_URI)
# 通过手动操作，访问 authorize_url 得到 access或者authorize code
url = c.authorize_url
print(url)
code = input()
c.set_code(code)
out = open("res.txt", 'w', encoding="utf8")
## 获取公共微博
d = c.get('statuses/public_timeline', count=200)
for i in range(len(d['statuses'])):
cc = d['statuses'][i]['text'].strip()
cc = cc.replace('\u200b', '').replace('\n', ' ').strip()
out.write(cc + '\n')
CALLBACK_URL = 'http://heisaman.xyz/callback' # callback url
n = 0
try:
token = {
u'access_token': u'2.001psIGCSorweBd556e626159iQzBB',
u'remind_in': u'157679999',
u'uid': u'1923041062',
u'expires_at': 1629809571
}
c = Client(APP_KEY, APP_SECRET, CALLBACK_URL, token=token)
# print token
# {u'access_token': u'2.001psIGCSorweBd556e626159iQzBB', u'remind_in': u'157679999', u'uid': u'1923041062', u'expires_at': 1629809571}
print(c.alive)
favorites_total_number = c.get('favorites/ids', count=1)['total_number']
print("共收藏了微博{0}条".format(favorites_total_number))
for i in range(favorites_total_number // 50 + 1):
print("第{0}页".format(i + 51))
res = c.get('favorites', count=50, page=i + 51)
print("{0}条收藏".format(len(res['favorites'])))
for favorite in res['favorites']:
n = n + 1
if collection.find({"_id": favorite['status']['id']}).count() > 0:
pass
else:
favorite['_id'] = favorite['status']['id']
if favorite['status']['created_at'] == '':
created_at = datetime.strptime(
'Wed Nov 28 15:00:00 +0800 2012',
class SinaWeibo:
def __init__(self,
username=wb_cfg.USER,
passwd=wb_cfg.PASSWD,
logger=None):
self.APP_KEY = wb_cfg.APP_KEY
self.APP_SECRET = wb_cfg.APP_SECRET
self.CALLBACK = wb_cfg.CALLBACK
self.USER = username
self.PASSWD = passwd
self.UID = wb_cfg.UID
self.log = logger
try:
self.client = Client(self.APP_KEY,
self.APP_SECRET,
self.CALLBACK,
token=None,
username=self.USER,
password=self.PASSWD)
log_info(u"微博模块", u"User %s Login Successful!" % self.USER,
self.log)
except Exception:
log_warn(u"微博模块", u"User %s Login Failed!" % self.USER, self.log)
def get_timeline(self):
if self.client:
return self.client.get('users/show', uid=self.UID)
def get_friend_status(self, cnt=20):
if self.client:
return self.client.get('statuses/friends_timeline',
uid=self.UID,
count=cnt)
def post_statuses(self, str_msg):
if self.client:
self.client.post('statuses/update', status=str_msg, uid=self.UID)
def repost_friend(self, iterval):
# 每相隔多久时间，转发一次朋友圈的微博
# 朋友圈
statuses = (self.get_friend_status(cnt=100))["statuses"]
if statuses:
for item in statuses:
#if item['text'].find('nicol:') != -1:
# log_info(u"微博模块",u"Alreadyed include me, skip it[%d]!\n" % item['id'], self.log)
# continue;
#if item['id'] == wb_cfg.UID :
# log_info(u"微博模块",u"My Own's weibo, skip it[%d]!\n" % item['id'], self.log)
# print item['text']
# continue;
if not REPOST_WHITE.has_key(item['user']['id']):
log_info(
u"微博模块",
u"Not in the repost_white list, skip [%d]!\n" %
item['id'], self.log)
continue
else:
try:
ret = self.client.post('statuses/repost',
id=item['id'],
status=u"[Nicol]强势转发微博",
is_comment=1)
except Exception, e:
log_warn(u"微博模块", u"Runtime Error:%s" % e, self.log)
continue
log_info(u"微博模块", u"Repost item for [%d]!\n" % item['id'],
self.log)
#等待一会儿
time.sleep(random.randint(300, 1000))
from weibo import Client
APP_KEY = '1521216146' # app key
APP_SECRET = '212c28b62505183820922d0f4f45e327' # app secret
CALLBACK_URL = 'http://heisaman.xyz/callback' # callback url
token = {
u'access_token': u'2.001psIGCSorweBd556e626159iQzBB',
u'remind_in': u'157679999',
u'uid': u'1923041062',
u'expires_at': 1629809571
}
c = Client(APP_KEY, APP_SECRET, CALLBACK_URL, token=token)
res = c.get('statuses/bilateral_timeline')
print("{0}".format(res))
class SinaCrawler:
def __init__(self, max_page):
self.session = None
self.MAX_PAGE = max_page
token = {u'access_token': u'2.00pE39sBn1UT7E61e7174d95TdYVED', u'remind_in': u'157679999', u'uid': u'1720813027', u'expires_at': 1575304674}
self.client = Client(app_key, app_secret, redirect_uri, token)
self.f = open("data", "w")
def __del__(self):
self.f.close()
def userlogin(self,username,password):
session = requests.Session()
url_prelogin = '******'
url_login = '******'
#get servertime,nonce, pubkey,rsakv
resp = session.get(url_prelogin)
json_data = re.search('\((.*)\)', resp.content).group(1)
data = json.loads(json_data)
servertime = data['servertime']
nonce = data['nonce']
pubkey = data['pubkey']
rsakv = data['rsakv']
# calculate su
su = base64.b64encode(urllib.quote(username))
#calculate sp
rsaPublickey= int(pubkey,16)
key = rsa.PublicKey(rsaPublickey,65537)
message = str(servertime) +'\t' + str(nonce) + '\n' + str(password)
sp = binascii.b2a_hex(rsa.encrypt(message,key))
postdata = {
'entry': 'weibo',
'gateway': '1',
'from': '',
'savestate': '7',
'userticket': '1',
'ssosimplelogin': '******',
'vsnf': '1',
'vsnval': '',
'su': su,
'service': 'miniblog',
'servertime': servertime,
'nonce': nonce,
'pwencode': 'rsa2',
'sp': sp,
'encoding': 'UTF-8',
'url': 'http://weibo.com/ajaxlogin.php?framelogin=1&callback=parent.sinaSSOController.feedBackUrlCallBack',
'returntype': 'META',
'rsakv' : rsakv,
}
resp = session.post(url_login,data = postdata)
# print resp.headers
login_url = re.findall('replace\(\'(.*)\'\)',resp.content)
#
respo = session.get(login_url[0])
self.session = session
def get_search_result(self, html_content):
""" get search result from the html content
Args:
html_content: str for storing html content of the search page
Return:
None
"""
#content = re.findall(r"\"pid\":\"pl_user_feedList\"(?P<tips>[\w\W]*?)", html_content)
html_content = html_content.strip()
content = re.findall(r"\"pid\":\"pl_wb_feedlist\"(?P<tips>[\w\W]*?)</script>", html_content)[0]
clean_content = string.replace(content, "\\\\", "\\")
search_result = re.findall(r"<div class=\\\"WB_cardwrap S_bg2 clearfix\\\" >(?P<tips>[\w\W]*?)<\\/div>\\n<\\/div>", clean_content)
return search_result
def get_person_info(self, person_info_html):
""" get person information from the html content
Args:
person_info_html : str indicating the personanl information
Return:
None
"""
txt = re.findall(r"=\\\"feed_list_content\\\">(?P<tips>[\w\W]*?)<\\/p>", person_info_html)
content = string.replace(txt[0], '\n', '')
content = string.replace(content, '\t', '')
tag = True
strs = ""
for w in content:
if w == '<':
tag = False
continue
if w == '>':
tag = True
continue
if tag:
strs += w
msg = strs.decode('unicode_escape').encode('utf8')
msg = string.replace(msg, '\n', '')
msg = string.replace(msg, '\t', '')
uid = re.findall("uid=(?P<tips>\d+?)&", person_info_html)[0]
time.sleep(random.random())
while True:
try:
info_dict = self.client.get('users/show', uid = uid)
break
except:
time.sleep(random.randint(1,40))
self.f.write('%s\t%s\t%s\t%s\t%s\t' % info_dict['screen_name'].encode('utf-8'), '\t', \
info_dict['gender'].encode('utf-8'), '\t', \
msg, '\t',\
info_dict['created_at'].encode('utf-8'), '\t', \
info_dict['location'].encode('utf-8'))
def do_search_page(self, page, query):
""" get search result of the page in the search html page
Args:
page : int indicating the number of the page
Return:
None
"""
search_url = "http://s.weibo.com/wb/%s&page=%d" % (query, page)
html_page = self.session.get(search_url)
all_results = self.get_search_result(html_page.content)
res_cnt = 1
for res in all_results:
print 'page %d result %d done' % (page, res_cnt)
res_cnt += 1
information = self.get_person_info(res)
def do_search(self, query):
""" do search
Args:
query : str indicating the query
Return:
None
"""
self.f.write('screen_name\tgender\trelated_msg\tregister_time\tlocation\n')
for page in range(1, self.MAX_PAGE + 1):
time.sleep(random.random())
self.do_search_page(page, query)
def search():
user = login_user(session)
if user:
client = Client(APP_KEY, APP_SECRET, CALLBACK_URL)
client.set_token(user["access_token"])
t = request.args.get('t', '')
q = request.args.get('q', '')
p = request.args.get('p', 1)
u = request.args.get('u', 0)
q = q.strip("@ \r\n\t")
t = t.strip("@ \r\n\t")
p = int(p)
if t != '':
retry = 0
page = p
n_page = p + 3
t_statuses = []
tar_screen_name = None
tar_profile_image_url = None
tar_location = None
while 1:
try:
if retry > 5:
break
statuses = client.get('statuses/user_timeline', uid=u, count=100, page=page)["statuses"]
weibo2db.statuses(statuses)
if tar_screen_name is None and len(statuses) > 0:
tar_profile_image_url = statuses[0]["user"]["profile_image_url"]
tar_screen_name = statuses[0]["user"]["name"]
tar_location = statuses[0]["user"]["location"]
for status in statuses:
if t in status["text"] or [t in status["retweeted_status"]["text"]
if "retweeted_status" in status else False][0]:
t_statuses.append(status)
if page == n_page:
break
else:
page += 1
except Exception, e:
app.logger.error(e)
retry += 1
if len(t_statuses) == 0:
flash(u"没有搜索到相关微博,请尝试下一页或者采用其他关键词")
statuses = t_statuses
p = page
else:
try:
target_user = client.get('users/show', screen_name=q)
except:
flash(u"您输入的昵称不存在,请重新输入")
return redirect(url_for('index'))
u = target_user["id"]
page = p
tar_screen_name = target_user["screen_name"]
tar_profile_image_url = target_user["profile_image_url"]
tar_location = target_user["location"]
try:
statuses = client.get('statuses/user_timeline', uid=u, count=50, page=page)["statuses"]
weibo2db.statuses(statuses)
except:
flash(u"获取微博信息失败,请刷新")
statuses = []
for i in xrange(len(statuses)):
weibo_url = "http://weibo.com/" \
+ str(statuses[i]["user"]["id"]) \
+ "/" + base62.mid_to_str(statuses[i]["mid"])
statuses[i]["weibo_url"] = weibo_url
screen_name = session["screen_name"]
profile_image_url = session["profile_image_url"]
return render_template('weibolist.html', btnuserpicvisible='inline',
btnloginvisible='none', t=t, q=q, p=int(p), u=u,
screen_name=screen_name, profile_image_url=profile_image_url,
tar_screen_name=tar_screen_name,
tar_profile_image_url=tar_profile_image_url,
tar_location=tar_location,
statuses=statuses)
if weibo_status.get('user', None):
user_name = weibo_status['user']['name']
user_profile_url = 'http://weibo.com/' + weibo_status['user'][
'profile_url']
weibo_content = md_escape(weibo_status['text'])
weibo_pic = weibo_status.get('original_pic', None)
weibo_pic_mid_thumb = weibo_status.get('bmiddle_pic', None)
weibo_pic_addition = ''
if weibo_pic:
weibo_pic_addition = u'([点击查看原始配图](%s))\n<img src="%s" style="max-height:300px;"/>' % (
weibo_pic, weibo_pic_mid_thumb)
return '[**%s**](%s)\n%s\n%s' % (user_name, user_profile_url,
weibo_content, weibo_pic_addition)
return ''
md_file = codecs.open('1.md', 'w+', 'utf-8')
for i in range(1, 100):
faved_weibos = c.get('favorites', count=20, page=i)
if not faved_weibos['favorites']:
break
for weibo in faved_weibos['favorites']:
md_string = ''
md_string += '- ' + status2md(weibo['status'])
if weibo['status'].get('retweeted_status', None):
md_string += '\n> ' + status2md(
weibo['status']['retweeted_status']) + '\n'
md_string += '\n---\n'
md_file.write(md_string)
if md_file:
md_file.close()
