def __init__(self, http=None):
self.http = http or TornadoHTTPClient()
if not http:
self.http.set_user_agent(
"Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Ubuntu Chromium/28.0.1500.71 Chrome/28.0.1500.71 Safari/537.36"
)
self.http.debug = getattr(config, "TRACE", False)
self.http.validate_cert = False
self.http.set_global_headers({"Accept-Charset": "UTF-8,*;q=0.5"})
self.url = "http://www.simsimi.com/func/reqN"
self.params = {
"lc": "zh",
"ft": 0.0,
"fl": "http://www.simsimi.com/talk.htm"
}
self.ready = False
self.fetch_kwargs = {}
if config.SimSimi_Proxy:
self.fetch_kwargs.update(proxy_host=config.SimSimi_Proxy[0],
proxy_port=config.SimSimi_Proxy[1])
self._setup_cookie()
def __init__(self, http = None):
self.http = http or TornadoHTTPClient()
#self.http.debug=True
self.result=[]
self.statment=[]
self.helpkeyword=['?',u'怎么',u'什么',u'鸭子','ee',u'好了','YY','yy',u'神马',u'啊',u'？',u'是么',u'依依',u'EE',u'BSD鸭子',u'能不能',u'多少',u'么']
pass
def __init__(self,
qid,
pwd,
client=None,
debug=False,
handle_msg_image=True):
self.handle_msg_image = handle_msg_image
self.http = TornadoHTTPClient()
self.http.set_user_agent(
"Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36"
" (KHTML, like Gecko) Ubuntu Chromium/28.0.1500.71 "
"Chrome/28.0.1500.71 Safari/537.36")
self.http.validate_cert = False
self.http.set_global_headers({"Accept-Charset": "UTF-8,*;q=0.5"})
self.http.debug = debug
self.qid = qid
self.__pwd = pwd
self.client = client
self.rc = random.randrange(0, 100)
self.aid = 1003903 # aid 固定
self.clientid = random.randrange(11111111, 99999999) # 客户端id 随机固定
self.msg_id = random.randrange(11111111, 99999999) # 消息id, 随机初始化
self.daid = 164
self.login_sig = None
self.ptwebqq = None
self.nickname = u"YouWillNeverGetIt"
self.vfwebqq = None
self.psessionid = None
self.stop_poll = False
# 检查是否验证码的回调
self.ptui_checkVC = lambda *r: r
# 是否需要验证码
self.require_check = None
self.require_check_time = None
# 是否开始心跳和拉取消息
self.poll_and_heart = None
self.login_time = None
self.hThread = None
# 验证图片
self.checkimg_path = tempfile.mktemp(".jpg")
self._lock_path = tempfile.mktemp()
self._wait_path = tempfile.mktemp()
self.group_sig = {} # 组签名映射, 用作发送临时消息(sess_message)
self.message_interval = 0.5 # 消息间隔
self.last_msg_time = time.time()
self.last_msg_content = None
self.last_msg_numbers = 0 # 剩余位发送的消息数量
WebQQRequest.hub = self
self.connecting = False
def find_next(self):
pprint('Start recover cookie')
s = TornadoHTTPClient(force_instance = True)
with open('cookie.txt') as f:
cookie_str = f.read()
s.set_global_headers({ 'Cookie': cookie_str })
resp = yield s.get('http://ehire.51job.com/CommonPage/JobsPostNumbList.aspx')
pprint('End recover cookie')
bs = BeautifulSoup(resp.body, "html.parser")
pprint(bs.find('b', {'class': 'info_att'}).text)
def __init__(self, qid, pwd, handler = None):
self.qid = qid # QQ 号
self.__pwd = pwd # QQ密码
self.nickname = None # 初始化QQ昵称
self.http = TornadoHTTPClient()
self.http.set_user_agent("Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Ubuntu Chromium/28.0.1500.71 Chrome/28.0.1500.71 Safari/537.36")
self.http.debug = TRACE
self.http.validate_cert = False
self.http.set_global_headers({"Accept-Charset": "UTF-8,*;q=0.5"})
self.msg_dispatch = MessageDispatch(self)
self.rc = random.randrange(0, 100)
self.aid = 1003903 # aid 固定
self.clientid = random.randrange(11111111, 99999999) # 客户端id 随机固定
self.msg_id = random.randrange(11111111, 99999999) # 消息id, 随机初始化
self.require_check = False # 是否需要验证码
self.poll_and_heart = False # 开始拉取消息和心跳
# 初始化WebQQ登录期间需要保存的数据
self.check_code = None
self.ptwebqq = None
self.require_check_time = None # 需要验证码的时间
self.checkimg_path = os.path.join(os.path.abspath(os.path.dirname(__file__)), "check.jpg")
self.friend_info = {} # 初始化好友列表
self.group_info = {} # 初始化组列表
self.group_sig = {} # 组签名映射, 用作发送临时消息(sess_message)
self.group_members_info = {} # 初始化组成员列表
self.mark_to_uin = {} # 备注名->uin的映射
self.daid = 164
self.login_sig = None
self.login_time = None # 登录的时间
self.last_msg_time = time.time()
self.last_msg_content = None
self.last_msg_numbers = 0 # 剩余位发送的消息数量
self.status_callback = None
self.poll_stoped = True # 获取消息是否停止
self.hThread = None # 心跳线程
#self.base_header = {"Referer":"https://d.web2.qq.com/cfproxy.html?v=20110331002&callback=1"}
self.base_header = {"Referer":"http://s.web2.qq.com/proxy.html?v=20110412001&callback=1&id=3"}
def __init__(self, qid, pwd):
self.qid = qid # QQ 号
self.__pwd = pwd # QQ密码
self.nickname = None # 初始化QQ昵称
self.http = TornadoHTTPClient()
self.http.set_user_agent(
"Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Ubuntu Chromium/28.0.1500.71 Chrome/28.0.1500.71 Safari/537.36"
)
self.http.debug = DEBUG
self.http.validate_cert = False
self.http.set_global_headers({"Accept-Charset": "UTF-8,*;q=0.5"})
self.msg_dispatch = MessageDispatch(self)
self.rc = random.randrange(0, 100)
self.aid = 1003903 # aid 固定
self.clientid = random.randrange(11111111, 99999999) # 客户端id 随机固定
self.msg_id = random.randrange(1111111, 99999999) # 消息id, 随机初始化
self.require_check = False # 是否需要验证码
self.poll_and_heart = False # 开始拉取消息和心跳
# 初始化WebQQ登录期间需要保存的数据
self.check_code = None
self.ptwebqq = None
self.check_data = None # 初始化检查时返回的数据
self.blogin_data = None # 初始化登录前返回的数据
self.friend_info = {} # 初始化好友列表
self.group_info = {} # 初始化组列表
self.group_sig = {} # 组签名映射, 用作发送临时消息(sess_message)
self.group_members_info = {} # 初始化组成员列表
self.hb_time = int(time.time() * 1000)
self.daid = 164
self.login_sig = None
self.login_time = None # 登录的时间
self.last_group_msg_time = time.time()
self.last_msg_content = None
self.last_msg_numbers = 0 # 剩余位发送的消息数量
self.base_header = {
"Referer":
"https://d.web2.qq.com/cfproxy.html?v=20110331002&callback=1"
}
def __init__(self, http=None):
self.http = http or TornadoHTTPClient()
if not http:
self.http.set_user_agent(
"Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Ubuntu Chromium/28.0.1500.71 Chrome/28.0.1500.71 Safari/537.36"
)
self.http.validate_cert = False
self.http.set_global_headers({"Accept-Charset": "UTF-8,*;q=0.5"})
self.url = "rest://www.simsimi.com/func/reqN"
self.params = {"lc": "ch", "ft": 0.0}
self.ready = False
self.fetch_kwargs = {}
self.fetch_kwargs.update(proxy_host='192.168.13.19', proxy_port='7777')
t = threading.Thread(target=self._setup_cookie())
t.start()
# print 'is match'
if type == "g" or type=="s" or type=="b":
print 'search'
if self.searcher.find(content):
result=self.searcher.search(content)
if result>=0 :
print 'result count:',result
return True
else:
self.content = content
return True
return False
pass
if __name__ == "__main__":
c=TornadoHTTPClient()
#c.start()
robot=SmartRobotPlugin(None,None,None,None)
#while True:
if robot.is_match(111, 'ss?', 'g')==True:
data=robot.get_result()
print "data:",data,type(data)
else:
print 'no found'
c=TornadoHTTPClient()
s=Searcher(c)
c.start()
#s.baidu_search('ss')
c.stop()
#
class Command(object):
http = TornadoHTTPClient()
_sim_try = {}
simsimi_proxy = False
def url_info(self, url, callback, isredirect=False):
""" 获取url信息
Arguments:
`url` - 链接
`callback` - 发送消息的回调
`isredirect` - 是否是重定向
"""
_url_info = partial(self._url_info,
callback=callback,
url=url,
isredirect=isredirect)
self.http.get(url, callback=_url_info)
def _url_info(self, resp, callback, url, isredirect=False):
""" 读取url_info的回调 """
meta_charset = re.compile(
br'<meta\s+http-equiv="?content-type"?'
'\s+content="?[^;]+;\s*charset=([^">]+'
')"?\s*/?>|<meta\s+charset="?([^">/"]+'
')"?\s*/?>', re.IGNORECASE)
body = ""
content = resp.body
c_type = resp.headers.get("Context-Type", "text/html")
if resp.code in [200]:
if c_type == "text/html":
charset = meta_charset.findall(content)
logging.info("Found charset {0!r} in url {1}".format(
charset, url))
if len(charset) == 1 and len(charset[0]) == 2:
charset = charset[0][0] if charset[0][0] else charset[0][1]
else:
charset = ""
if charset.lower().strip() == "gb2312":
charset = "gbk"
if charset:
ucont = content.lower().decode(charset).encode(
"utf-8").decode("utf-8")
else:
ucont = content.lower().decode("utf-8")
parser = etree.HTML(ucont)
title = parser.xpath(u"//title")
title = title[0].text if len(title) >= 1 else None
if title:
body += u"网页标题: " + title.replace("\r", "").replace(
"\n", "")
if isredirect:
body += u"(重定向到:{0})".format(url)
elif resp.code in [302, 301]:
dst = resp.headers.get("Location")
self.url_info(dst, callback, True)
else:
body = u"({0} {1} {2})".format(url, resp.code,
httplib.responses[resp.code])
if body:
callback(body)
def _eurl_info(self, errcode, errmsg, url, callback):
""" 处理url_info错误 """
body = u"({0} {1})".format(url, errmsg)
callback(body)
def py(self, code, callback):
""" 执行Python代码
Arguments:
`code` - 要执行的代码
`callback` - 发送消息的回调
"""
url = "http://pythonec.appspot.com/run"
#url = "http://localhost:8080/run"
params = [("code", code.encode("utf-8"))]
read_py = partial(self.read_py, callback=callback)
self.http.post(url, params, callback=read_py)
def read_py(self, resp, callback):
""" 读取执行Python代码的返回 """
data = resp.body
try:
result = json.loads(data)
status = result.get("status")
if status:
content = u"OK: " + result.get("out")
else:
content = u"ERR: " + result.get("err")
except ValueError:
logging.warn(traceback.format_exc())
content = u"我出错了, 没办法执行, 我正在改"
callback(content)
def shell(self, session, statement, callback):
""" 实现Python Shell
Arguments:
`session` - 区别用户的shell
`statement` - Python语句
`callback` - 发送结果的回调
"""
if statement.strip() in ["cls", "clear"]:
url = "http://pythonec.appspot.com/drop"
params = [
("session", session),
]
else:
url = "http://pythonec.appspot.com/shell"
#url = "http://localhost:8080/shell"
params = [("session", session),
("statement", statement.encode("utf-8"))]
def read_shell(resp, callback):
data = resp.body
if not data:
data = "OK"
callback(data.decode("utf-8"))
return
callback = partial(read_shell, callback=callback)
self.http.get(url, params, callback=callback)
def paste(self, code, callback, typ="text"):
""" 贴代码 """
url = "http://paste.linuxzen.com"
params = [("class", typ), ("code", code.encode("utf-8")),
("paste", "ff")]
callback = partial(self.read_paste, oldurl=url, callback=callback)
self.http.post(url, params, callback=callback)
def read_paste(self, resp, oldurl, callback):
""" 读取贴代码结果, 并发送消息 """
if resp.code == 302:
url = resp.headers.get("Location")
else:
url = resp.effective_url
if url != oldurl:
content = url
callback(content)
def teach(self, say, response):
url = "http://paste.linuxzen.com/bot/teach"
params = (("say", say.encode("utf-8")), ("res",
response.encode("utf-8")))
logging.info(u"Teach our bot {0}/{1}".format(say, response))
self.http.get(url, params)
def talk(self, say, callback):
url = "http://paste.linuxzen.com/bot/talk"
params = (("say", say.encode("utf-8")), )
def callback(resp):
data = resp.body
r = json.loads(data)
if r.get("status"):
callback(r.get("response"))
else:
self.simsimi(say, callback)
self.http.get(url, params, callback=callback)
def simsimi(self, content, callback):
""" simsimi 小黄鸡 """
msg_url = "http://www.simsimi.com/func/req"
msg_params = (("msg", content.encode("utf-8")), ("lc", "ch"))
headers = {
"Referer": "http://www.simsimi.com/talk.htm?lc=ch",
"X-Requested-With": "XMLHttpRequest"
}
def read_simsimi(resp):
result = resp.body
if result:
try:
response = json.loads(result)
res = response.get("response")
if is_black_msg(res):
return self.simsimi(content, callback)
if not res or (res and
res.startswith("Unauthorized access!.")):
if not self._sim_try.has_key(content):
self._sim_try[content] = 0
if self._sim_try.get(content) < 10:
logging.warn(
"SimSimi error with response {0}".format(res))
self._sim_try[content] += 1
self.simsimi(content, callback)
else:
self._sim_try[content] = 0
callback(u"T^T ip被SimSimi封了, 无法应答")
return
else:
self._sim_try[content] = 0
callback(res)
self.teach(content, res)
except ValueError:
logging.warn(traceback.format_exc())
logging.warn(
"SimSimi error with response {0}".format(result))
#self.simsimi(content, callback)
callback(u"呵呵")
kw = {"headers": headers, "callback": read_simsimi}
if SimSimi_Proxy:
kw.update(proxy=SimSimi_Proxy)
self.http.get(msg_url, msg_params, **kw)
def cetr(self, source, callback, web=False):
""" 调用有道接口进行英汉互译 """
key = YOUDAO_KEY
keyfrom = YOUDAO_KEYFROM
source = source.encode("utf-8")
url = "http://fanyi.youdao.com/openapi.do"
params = [("keyfrom", keyfrom), ("key", key), ("type", "data"),
("doctype", "json"), ("version", 1.1), ("q", source)]
callback = partial(self.read_cetr, callback=callback, web=web)
self.http.get(url, params, callback=callback)
def read_cetr(self, resp, callback, web):
""" 读取英汉翻译的结果 """
"""
try:
buf = StringIO(source)
with gzip.GzipFile(mode = "rb", fileobj = buf) as gf:
data = gf.read()
except:
logging.warn(traceback.format_exc())
data = source
"""
try:
result = json.loads(resp.body)
except ValueError:
logging.warn(traceback.format_exc())
body = u"error"
else:
errorCode = result.get("errorCode")
if errorCode == 0:
query = result.get("query")
r = " ".join(result.get("translation"))
basic = result.get("basic", {})
body = u"{0}\n{1}".format(query, r)
phonetic = basic.get("phonetic")
if phonetic:
ps = phonetic.split(",")
if len(ps) == 2:
pstr = u"读音: 英 [{0}] 美 [{1}]".format(*ps)
else:
pstr = u"读音: {0}".format(*ps)
body += u"\n" + pstr
exp = basic.get("explains")
if exp:
body += u"\n其他释义:\n\t{0}".format(u"\n\t".join(exp))
if web:
body += u"\n网络释义:\n"
web = result.get("web", [])
if web:
for w in web:
body += u"\t{0}\n".format(w.get("key"))
vs = u"\n\t\t".join(w.get("value"))
body += u"\t\t{0}\n".format(vs)
if errorCode == 50:
body = u"无效的有道key"
if not body:
body = u"没有结果"
callback(body)
def send_msg(self, msg, callback, nick=None):
if len(msg) <= MAX_LENGTH:
body = nick + msg if nick else msg
callback(body)
else:
callback = partial(self.send_msg, callback=callback, nick=nick)
self.paste(msg, callback)
def setUp(self):
self.http = TornadoHTTPClient()
self.http.debug = True
def setUp(self):
super(TornadoHTTPClientCoroutineTest, self).setUp()
self.http = TornadoHTTPClient()
self.http.debug = True
def __init__(self, message_bus):
self._message_bus = message_bus # 消息总线
self._logger = get_logger() # 日志
self._http_stream = TornadoHTTPClient()
self._honor = Honor()
if (content.startswith("<") and content.endswith(">")) or\
(content.startswith(u"《") and content.endswith(u"》")):
self._name = content.strip("<").strip(">").strip(u"《")\
.strip(u"》")
if not self._name.strip():
return False
if self.douban is None:
self.douban = DoubanReader(self.http)
return True
return False
def handle_message(self, callback):
self.douban.search(self._name, callback)
if __name__ == "__main__":
from tornadohttpclient import TornadoHTTPClient
def cb(b):
print b
douban = DoubanReader(TornadoHTTPClient())
douban.search(u"百年孤独", cb)
douban.search(u"鸟哥的私房菜", cb)
douban.search(u"论语", cb)
douban.search(u"寒战", cb)
douban.search(u"阿凡达", cb)
douban.search(u"创战记", cb)
douban.search(u"简单爱", cb)
TornadoHTTPClient().start()
def find(self):
pprint('Into tornadohttpclient')
s = TornadoHTTPClient(force_instance = True)
pprint('Start login')
f = yield s.get('http://ehire.51job.com')
soup = BeautifulSoup(f.body, "html.parser")
hidAccessKey = soup.find('input', {'name': 'hidAccessKey'})['value']
fksc = soup.find('input', {'name': 'fksc'})['value']
hidEhireGuid = soup.find('input', {'name': 'hidEhireGuid'})['value']
headers = {
'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8',
'Content-Type': 'application/x-www-form-urlencoded',
'Origin': 'http://ehire.51job.com',
'Referer': 'http://ehire.51job.com/MainLogin.aspx',
'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_11_5) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/53.0.2785.143 Safari/537.36'
}
data = {'ctmName': '大岂网络',
'userName': '******',
'password': '******',
'oldAccessKey': hidAccessKey,
'langtype': 'Lang=&Flag=1',
'sc': fksc,
'ec': hidEhireGuid,
'isRememberMe': 'True'
}
res = yield s.post('https://ehirelogin.51job.com/Member/UserLogin.aspx', data=data, headers=headers)
pprint('End login')
pprint('Start force')
try:
soup = BeautifulSoup(res.body, "html.parser")
viewState = soup.find('input', {'name': '__VIEWSTATE'})['value']
partURL = soup.find('form', {'id': 'form1'})['action']
URL = 'http://ehire.51job.com/Member/' + partURL
headers = {
'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8',
'Content-Type': 'application/x-www-form-urlencoded',
'Origin': 'http://ehire.51job.com',
'Referer': URL,
'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_11_5) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/53.0.2785.143 Safari/537.36'
}
data = {'__EVENTTARGET': 'gvOnLineUser',
'__EVENTARGUMENT': 'KickOut$0',
'__VIEWSTATE': viewState
}
res = yield s.post(URL, data=data, headers=headers)
except: pass # 有时不需要下线
pprint('End force')
pprint('Start fetch remain')
resp = yield s.get('http://ehire.51job.com/CommonPage/JobsPostNumbList.aspx')
pprint('End fetch remain')
bs = BeautifulSoup(resp.body, "html.parser")
pprint(bs.find('b', {'class': 'info_att'}).text)
pprint('###Cookie###')
pprint(s.cookie)
with open('cookie.txt', 'w') as f:
f.write(s.cookie)
#!/usr/bin/env python
#coding=utf8
from tornado import gen
from tornado.ioloop import IOLoop
from tornadohttpclient import TornadoHTTPClient
import json
# 实例化
http = TornadoHTTPClient()
@gen.coroutine
def get():
headers = dict((("content-type","application/json"),("Accept-Charset","utf8"),("Authorization","token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
# 发出get请求
# response = yield #http.post("http://ipsapro.isoftstone.com:8081/api/user/login",'{"strUser":"******","strPwd":"e10adc3949ba59abbe56e057f20f883ee10adc3949ba59abbe56e057f20f883e"}',headers=headers)
response = yield http.post("http://ipsapro.isoftstone.com:8081/api/Department/GetDepartment",'',headers=headers);
# print(response.body)
fo = open("department.txt", "wb")
#j=json.loads(response.body)
#str_json=json.dumps(j['departments'],encoding="gbk",ensure_ascii=False)
str_json=response.body
fo.write(str_json)
IOLoop.instance().run_sync(get)
