def reply_sina_club(post_url, src):
""" 新浪论坛回复函数
- Name: 新浪论坛18646492184
- Feature: (forum|club).*.sina.com.cn
- Captcha: YES
- Login: YES
@param post_url: 帖子地址
@type post_url: str
@param src: 用户名，密码，回复内容，等等。
@type src: dict
@return: 是否回复成功
@rtype: bool
"""
logger = utils.RAPLogger(post_url)
sess = utils.RAPSession(src)
# Step 1: 登录
if not login_sina(sess, src):
logger.error(' Login Error')
return (False, str(logger))
logger.info(' Login OK')
# Step 2: 回复
resp = sess.get(post_url)
host = utils.get_host(post_url)
# 获取回复地址
reply_url = re.findall(r'id=\"postform\" action=\"(.*?)\"',
resp.content)[0]
soup = BeautifulSoup(resp.content)
# 获取回复form
form = soup.find('form', attrs={'id': 'postform'})
# 构造回复参数
payload = utils.get_datadic(form)
payload['message'] = src['content'].decode('utf8').encode(CHARSET)
# 替换回复地址中的特殊符号
reply_url = reply_url.replace('&', '&')
# 发送回复post包
resp = sess.post(reply_url,
data=payload,
headers={
'Origin': utils.get_host(post_url),
'Referer': post_url
})
post_times = 0
# 验证是否成功，如果失败再次发送
# 失败可能原因：验证码错误
while 'postform' not in resp.content \
and post_times < src['TTL']:
# 限制最大发送次数
post_times = post_times + 1
logger.info(' reply need captcha')
# 获取验证码图片
captcha = sess.get(host + 'seccode.php',
headers={
'Accept': config.accept_image,
'Referer': reply_url
})
# 获取验证码字符串
seccode = utils.crack_captcha(captcha.content)
logger.info(' seccode:' + seccode)
# 回复参数中增加验证码
payload['seccodeverify'] = seccode.decode(CHARSET)
# 发送回复post包
resp = sess.post(reply_url,
data=payload,
headers={
'Origin': utils.get_host(post_url),
'Referer': post_url
})
# 若指定字样出现在response中，表示回复成功
if 'postform' not in resp.content:
logger.error(' Reply Error')
return (False, str(logger))
logger.info(' Reply OK')
return (True, str(logger))
def login_sina(sess, src):
""" 新浪登录函数
@param sess: requests.Session()
@type sess: Session
@param post_url: 帖子地址
@type post_url: str
@param src: 用户名，密码，回复内容，等等。
@type src: dict
@return: 是否登录成功
@rtype: bool
"""
url_prelogin = '******'
url_login = '******'
# 获取prelogin中各项参数：servertime, nonce, pubkey, rsakv, pcid
resp = sess.get(url_prelogin)
json_data = re.findall(r'\((.*?)\)', resp.content)[0]
data = json.loads(json_data)
servertime = data['servertime']
nonce = data['nonce']
pubkey = data['pubkey']
rsakv = data['rsakv']
pcid = data['pcid']
# 用户名：采用base64加密
su = base64.b64encode(urllib.quote(src['username']))
# 密码：采用rsa加密
rsaPublickey = int(pubkey, 16)
key = rsa.PublicKey(rsaPublickey, 65537)
message = str(servertime) + '\t' + str(nonce) + '\n' + str(src['password'])
sp = binascii.b2a_hex(rsa.encrypt(message, key))
# 获取验证码图片
captcha_URI = sess.get(
'http://login.sina.com.cn/cgi/pin.php?r=39011430&s=0&p=' + pcid,
headers={'Accept': config.accept_image})
# 获取验证码字符串
captcha = utils.crack_captcha(captcha_URI.content)
print 'captcha:' + captcha
payload = {
'entry': 'weibo',
'gateway': '1',
'from': '',
'savestate': '7',
'userticket': '1',
'pagerefer': 'http://www.baidu.com/',
'ssosimplelogin': '******',
'vsnf': '1',
'pcid': pcid,
'door': captcha,
'su': su,
'service': 'miniblog',
'servertime': servertime,
'nonce': nonce,
'pwencode': 'rsa2',
'rsakv': rsakv,
'sp': sp,
'sr': '1366*768',
'prelt': '168',
'encoding': 'UTF-8',
'url':
'http://weibo.com/ajaxlogin.php?framelogin=1&callback=parent.sinaSSOController.feedBackUrlCallBack',
'returntype': 'META'
}
resp = sess.post(
url_login,
data=payload,
headers={
'Referer':
'http://weibo.com',
'User-Agent':
'Mozilla/5.0 (Windows NT 6.3; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/37.0.2062.124 Safari/537.36'
})
retcode = re.findall(r'retcode=(\d+)', resp.content)[0]
print 'retcode: ' + retcode
if retcode == '0':
return True
else:
reason = re.findall(r'reason=(.+)&', resp.content)[0]
print 'reason: ' + urllib.unquote(reason).decode('GBK')
return False
def validateuser(self, uid):
s = requests.session()
cookies = {
'anonymid': 'i8pg5nhd-shfdcd',
'_r01_': '1',
'JSESSIONID': 'abc6gyMzwvHPk4Az8nN0u',
'wp': '0',
'jebe_key':
'35c0ba4a-c1fa-454c-bf08-3cd0517227a4%7Ce65290594db334b483ac1f24d6999fef%7C1430884448428%7C1%7C1430885122107',
'_urm_378384894': '9999',
'depovince': 'BJ',
'jebecookies': 'e1c7f34b-675d-48d9-873c-a6327590c04e|||||',
'ick_login': '******',
'_de': 'E6CA621BCBC30E9A85E798EF221DF2AF',
'p': '920950803139a28ca9a4c028f1c2846e4',
'first_login_flag': '1',
'ln_uact': '18345174475',
'ln_hurl':
'http://hdn.xnimg.cn/photos/hdn421/20140206/2325/h_main_TZb3_97690001dbe1111a.jpg',
't': '2582a0a96c3887f092040edd842ea33b4',
'societyguester': '2582a0a96c3887f092040edd842ea33b4',
'id': '378384894',
'xnsid': 'd7c2bea1',
'__utma': '10481322.1851133621.1430901819.1430901819.1430901819.1',
'__utmc': '10481322',
'__utmz':
'10481322.1430901819.1.1.utmcsr=share.renren.com|utmccn=(referral)|utmcmd=referral|utmcct=/share/v7/161125632',
'alxn': 'a5d9878e44be799cc3e99efcab2d3dcd',
'mt': 'Jvfhn7u-wG7PdteezqsqEK',
'cp_config': '2',
'ver': '7.0',
'loginfrom': 'null',
'jebe_key':
'35c0ba4a-c1fa-454c-bf08-3cd0517227a4%7Ce65290594db334b483ac1f24d6999fef%7C1430910523708%7C1',
'wp_fold': '0',
'l4pager': '0'
}
r = s.get(
'http://www.renren.com/validateuser.do?id=' + str(uid),
cookies=cookies,
headers={
'Pragma':
'no-cache',
'Referer':
'http://www.renren.com/343633795/profile',
'User-Agent':
'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/40.0.2214.94 Safari/537.36'
})
soup = BeautifulSoup(r.content)
form = soup.find('form', attrs={'name': 'valiateUserForm'})
payload = utils.get_datadic(form)
r = s.get('http://icode.renren.com/getcode.do?t=ninki&rnd=' +
str(int(time.time() * 1000)),
cookies=cookies,
headers={
'Accept': 'image/webp,*/*;q=0.8',
'Referer': 'http://www.renren.com/validateuser.do'
})
seccode = utils.crack_captcha(r.content)
payload['icode'] = seccode
payload['requestToken'] = '-295732589'
payload['_rtk'] = 'ba2078ed'
print payload
r = s.post(
'http://www.renren.com/validateuser.do',
data=payload,
cookies=cookies,
headers={
'Accept':
'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8',
'Host':
'www.renren.com',
'Origin':
'http://www.renren.com',
'Pragma':
'no-cache',
'Referer':
'http://www.renren.com/validateuser.do?id=' + str(uid),
'User-Agent':
'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/40.0.2214.94 Safari/537.36'
})
print r.url
def post_sina_blog(post_url, src):
""" 新浪博客发帖函数
@param post_url: 板块地址 blog.sina.com.cn
@type post_url: str
@param src: 用户名，密码，等等。
@type src: dict
@return: 是否发帖成功
@rtype: bool
"""
logger = utils.RAPLogger(post_url)
sess = utils.RAPSession(src)
# Step 1: 登录
is_login = False
i = 0
while not is_login and i < src['TTL']:
i += 1
is_login = login_sina(sess, src)
if not is_login:
logger.error(' Login Error')
return (False, str(logger))
logger.info(' Login OK')
resp = sess.get(
'http://control.blog.sina.com.cn/admin/article/article_add.php')
soup = BeautifulSoup(resp.content)
# 获取回复form
form = soup.find('form', attrs={'id': 'editorForm'})
payload = utils.get_datadic(form)
payload['blog_title'] = src['subject']
payload['blog_body'] = src['content']
payload['conlen'] = 9
payload['x_cms_flag'] = 0
payload['x_rank'] = ''
#print payload
resp = sess.post(form['action'], data=payload)
jsonData = json.loads(resp.content)
logger.info(resp.content)
if jsonData['code'] == u'B06001':
url = 'http://blog.sina.com.cn/s/blog_' + jsonData['data'] + '.html'
logger.info(' Post OK')
return (url, str(logger))
while jsonData['code'] == u'B06013' and src['TTL']:
src['TTL'] = src['TTL'] - 1
captcha = sess.get(
'http://interface.blog.sina.com.cn/riaapi/checkwd_image.php?r=0.8578676988836378',
headers={'Accept': config.accept_image})
# 获取验证码字符串
seccode = utils.crack_captcha(captcha.content)
logger.info(' captcha:' + seccode)
payload['checkword'] = seccode
resp = sess.post(form['action'], data=payload)
jsonData = json.loads(resp.content)
logger.info(resp.content)
if jsonData['code'] == u'B06001':
url = 'http://blog.sina.com.cn/s/blog_' + jsonData['data'] + '.html'
logger.info(' Post OK')
return (url, str(logger))
logger.info(' Post Error')
return ('', str(logger))
def login_qq(sess, src):
""" QQ登录函数
@param sess: requests.Session()
@type sess: Session
@param src: 用户名，密码，回复内容，等等。
@type src: dict
@return: 是否登录成功
@rtype: bool
"""
# 获取验证码图片
url = 'http://i.qq.com'
resp = sess.get(url)
soup = BeautifulSoup(resp.content)
url = soup.select('#login_frame')[0]['src']
resp = sess.get(url)
login_sig = re.findall('login_sig:"(.*?)"', resp.content)[0]
# 构造获取验证码图片参数
par = {
'appid': '549000912',
'js_type': 1,
'js_ver': 10116,
'login_sig': login_sig,
'r': 0.8861454421075537,
'regmaster': "",
'pt_tea': "1",
'u1': "http://qzs.qq.com/qzone/v5/loginsucc.html?para=izone",
'uin': src['username']
}
resp = sess.get('http://check.ptlogin2.qq.com/check', params=par)
print resp.content
_, vcode, uin, _, _ = re.findall(r'\'(.*?)\'', resp.content)
url = 'http://captcha.qq.com/getimage?uin=' + src[
'username'] + '&aid=549000912&cap_cd=' + vcode + '&0.5720198110211641'
resp = sess.get(url, headers={
'Accept': config.accept_image,
})
# 获取验证码字符串
seccode = utils.crack_captcha(resp.content)
#构造参数
payload = {
'u': src['username'],
'verifycode': seccode,
'pt_vcode_v1': 0,
'pt_verifysession_v1': sess.s.cookies['verifysession'],
'p': get_pwd(src['password'], uin, seccode),
'pt_randsalt': 0,
'u1': 'http://qzs.qq.com/qzone/v5/loginsucc.html?para=izone',
'ptredirect': 0,
'h': 1,
't': 1,
'g': 1,
'from_ui': 1,
'ptlang': 2052,
'action': '5-4-1427091605160',
'js_ver': 10116,
'js_type': 1,
'login_sig': login_sig,
'pt_uistyle': 32,
'aid': 549000912,
'daid': 5,
'pt_qzone_sig': 1,
'': ''
}
# for k,v in payload.items():
# print k, v
resp = sess.get('http://ptlogin2.qq.com/login', params=payload)
print resp.content
if '登录成功' in resp.content:
return True
return False
def reply_163_blog(post_url, src):
""" 网易博客回复函数
- Name: 网易博客
- Feature: blog.163.com
- Captcha: YES
- Login: YES
@param post_url: 博客地址
@type post_url: str
@param src: 用户名，密码，回复内容，等等。
@type src: dict
@return: 是否回复成功
@rtype: bool
"""
logger = utils.RAPLogger(post_url)
sess = utils.RAPSession(src)
# Step 1: 登录
if not login_163(sess, src):
logger.error(' Login Error')
return (False, str(logger))
logger.info(' Login OK')
# Step 2: 验证码
resp = sess.get(post_url)
parent_id = re.findall(r'userId:(.*?),', resp.content)[0]
# 获取验证码图片
resp = sess.get('http://api.blog.163.com/cap/captcha.jpgx?'
'parentId=' + parent_id,
headers={
'Accept': config.accept_image,
'Referer': post_url,
})
# 获取验证码字符串
seccode = utils.crack_captcha(resp.content)
logger.info(' seccode:' + seccode)
# Step 3: 提交回复
resp = sess.get(post_url)
soup = BeautifulSoup(resp.content)
meta = soup.find('meta', attrs={'name': 'author'})
# 从页面中获取各项参数
page_id = re.findall('id:\'(.*?)\'', resp.content)[0]
parent_id = re.findall('parentId=(.*?)&', resp.content)[0]
author_0 = urllib.quote(
meta.attrs['content'].split(',')[0].encode(CHARSET))
author_1 = urllib.quote(
meta.attrs['content'].split(',')[1].encode(CHARSET))
content = urllib.quote(src['content'] + '<wbr>')
# 构造回复参数
payload = 'callCount=1\n' +\
'scriptSessionId=${scriptSessionId}187\n' +\
'c0-scriptName=BlogBeanNew\n' +\
'c0-methodName=addBlogComment\n' +\
'c0-id=0\n' +\
'c0-e1=string:' + page_id + '\n' +\
'c0-e2=number:' + parent_id + '\n' +\
'c0-e3=string:\n' +\
'c0-e4=string:''' + content + '\n' +\
'c0-e5=string:''' + src['username'] + '\n' +\
'c0-e6=string:\n' +\
'c0-e7=number:-1\n' +\
'c0-e8=number:-1\n' +\
'c0-e9=number:''' + parent_id + '\n' +\
'c0-e10=string:''' + author_0 + '\n' +\
'c0-e11=string:''' + author_1 + '\n' +\
'c0-e12=bool:true\n' +\
'c0-param0=Object_Object:' \
'{blogId:reference:c0-e1,' \
'blogUserId:reference:c0-e2,' \
'blogTitle:reference:c0-e3,' \
'content:reference:c0-e4,' \
'publisherNickname:reference:c0-e5,' \
'publisherEmail:reference:c0-e6,' \
'mainComId:reference:c0-e7,' \
'replyComId:reference:c0-e8,' \
'replyToUserId:reference:c0-e9,' \
'replyToUserName:reference:c0-e10,' \
'replyToUserNick:reference:c0-e11,' \
'synchMiniBlog:reference:c0-e12}\n' +\
'c0-param1=string:''' + seccode + '\n' +\
'c0-param2=bool:false\n' +\
'batchId=118652'
# 请求头设置
headers = {
'Content-Type': 'text/plain',
'Origin': 'http://api.blog.163.com',
'Referer': 'http://api.blog.163.com/crossdomain.html?t=20100205',
'Accept-Language': 'zh-CN,zh;q=0.8,en;q=0.6'
}
# 发送回复post包
resp = sess.post(
'http://api.blog.163.com/xinluduwu/dwr/'
'call/plaincall/BlogBeanNew.addBlogComment.dwr',
data=payload,
headers=headers)
# 若指定字样出现在response中，表示回复成功
if '_remoteHandleCallback' not in resp.content:
logger.info(resp.content)
logger.error(' Reply Error')
return (False, str(logger))
logger.info(' Reply OK')
return (True, str(logger))
def reply_163_bbs(post_url, src):
""" 网易论坛回复函数
- Name: 网易论坛
- Feature: bbs.*.163.com/bbs/
- Captcha: YES
- Login: YES
@param post_url: 帖子地址
@type post_url: str
@param src: 用户名，密码，回复内容，等等。
@type src: dict
@return: 是否回复成功
@rtype: bool
"""
logger = utils.RAPLogger(post_url)
sess = utils.RAPSession(src)
# Step 1: 登录
if not login_163(sess, src):
logger.error(' Login Error')
return (False, str(logger))
logger.info(' Login OK')
# Step 2: 验证码
host = utils.get_host(post_url)
logger.info(host)
page = sess.get(post_url)
# 获取各项参数
board_id = re.findall('boardId = \"(.*?)\"', page.content)[0]
thread_id = re.findall('threadId = \"(.*?)\"', page.content)[0]
# 当前时间戳
timestamp = str(time.time())
# 询问是否需要验证码
resp = sess.post(host + 'v2/post/replyCheck/' + board_id + '/' +
thread_id + '/?timestamp=' + timestamp,
headers={
'X-Requested-With': 'XMLHttpRequest',
'Origin': host,
'Referer': post_url,
'Accept-Language': 'zh-CN,zh;q=0.8,en;q=0.6'
})
# 询问结果
check_code = re.findall('\"checkCode\":\"(.*?)\",', resp.content)[0]
logger.info(check_code)
seccode = ''
validate_sucess = False
post_times = 0
# 如果需要验证码
if check_code == '1':
# 询问验证码是否正确，如果不正确再次发送
while not validate_sucess \
and post_times < src['TTL']:
# 限制最大发送次数
post_times = post_times + 1
# 获取验证码图片
resp = sess.get(host + 'v2/checkcode/codeimg?timestamp=' +
timestamp,
headers={
'Accept': config.accept_image,
'Referer': post_url,
})
# 获取验证码字符串
seccode = utils.crack_captcha(resp.content)
logger.info(' seccode:' + seccode)
# 发送验证码，询问是否正确
payload = {'code': seccode.encode('utf-8')}
resp = sess.post(host + 'v2/checkcode/validate',
data=payload,
headers={
'Origin': host,
'Referer': post_url,
})
logger.info(resp.content)
validate_sucess = '"code":1' in resp.content
# Step 3: 回复
# 构造回复参数
payload = {
'checkcode': seccode,
'content': src['content'].decode('utf8').encode(CHARSET),
'title': re.findall('<title>(.*?)</title>', page.content)[0],
'boardId': board_id,
'threadId': thread_id
}
# 发送回复post包
resp = sess.post(host + 'v2/post/doReply',
data=payload,
headers={
'Referer': post_url,
})
# 若指定字样出现在response中，表示回复成功
if '\"message\">' in resp.content:
logger.error(' Reply Error ' + re.findall(
'\"message\">(.*?)</td>', resp.content.decode(CHARSET))[0])
return (False, str(logger))
logger.info(' Reply OK')
return (True, str(logger))
def reply_163_news(post_url, src):
""" 网易新闻回复函数
- Name: 网易新闻
- Feature: news.163.com/[0-9]
- Captcha: YES
- Login: YES
@param post_url: 新闻地址
@type post_url: str
@param src: 用户名，密码，回复内容，等等。
@type src: dict
@return: 是否回复成功
@rtype: bool
"""
logger = utils.RAPLogger(post_url)
sess = utils.RAPSession(src)
# Step 1: 登录
if not login_163(sess, src):
logger.error(' Login Error')
return (False, str(logger))
logger.info(' Login OK')
# Step 2: 验证码
resp = sess.get(post_url)
# 获取各项参数
board_id = re.findall('boardId = \"(.*?)\"', resp.content)[0]
thread_id = re.findall('threadId = \"(.*?)\"', resp.content)[0]
comments_url = "http://comment.news.163.com/" + \
board_id + "/" + thread_id + ".html"
# 构造请求头
headers = {
'X-Requested-With': 'XMLHttpRequest',
'Origin': 'http://comment.news.163.com',
'Referer': comments_url,
'Accept-Language': 'zh-CN,zh;q=0.8,en;q=0.6'
}
# 询问是否需要验证码
resp = sess.get(
'http://comment.news.163.com/reply/needvalidate.jsp?'
'time=1413303328581',
headers=headers)
# 询问结果
need_validate = re.findall('needValidate:([0-9])', resp.content)[0]
seccode = ''
validate_sucess = False
post_times = 0
# 如果需要验证码
if need_validate == '1':
# 询问验证码是否正确，如果不正确再次发送
while not validate_sucess \
and post_times < src['TTL']:
# 限制最大发送次数
post_times = post_times + 1
# 获取验证图片
resp = sess.get(
'http://comment.news.163.com/reply/'
'auth/validatecode.jsp?rnd=',
headers={
'Accept': config.accept_image,
'Referer': comments_url,
})
# 获取验证码字符串
seccode = utils.crack_captcha(resp.content)
logger.info(' seccode:' + seccode)
# 询问验证码是否正确
resp = sess.get('http://comment.news.163.com/reply/'
'isValidateCodeValid.jsp?'
'validateCode=' + seccode,
headers={
'Referer': comments_url,
})
logger.info(resp.content)
validate_sucess = 'true' in resp.content
# Step 3: 回复
# 构造回复参数
payload = {
'board': board_id,
'quote': '',
'threadid': thread_id,
'hidename': False,
'username': src['username'],
'body': src['content'],
'isTinyBlogSyn': 1,
'flag': '',
'validateCode': seccode,
}
# 发送回复post包
resp = sess.post('http://comment.news.163.com/reply/dopost.jsp',
data=payload,
headers=headers)
# 若指定字样出现在response中，表示回复成功
if '网易首页' not in resp.content:
logger.error(' Reply Error')
return (False, str(logger))
logger.info(' Reply OK')
return (True, str(logger))
def post_163_blog(post_url, src):
""" 网易博客发帖函数
@param post_url: 板块地址 blog.163.com
@type post_url: str
@param src: 用户名，密码，回复内容，等等。
@type src: dict
@return: 是否发帖成功
@rtype: bool
"""
logger = utils.RAPLogger(post_url)
sess = utils.RAPSession(src)
# Step 1: 登录
if not login_163(sess, src):
logger.error(' Login Error')
return (False, str(logger))
logger.info(' Login OK')
username = src['username'].split('@')[0]
resp = sess.get('http://' + username +
'.blog.163.com/blog/getBlog.do?fromString=bloglist')
parentId = re.findall(r'parentId=(\d+)', resp.content)[0]
soup = BeautifulSoup(resp.content)
# 获取回复form
form = soup.find('form', attrs={'target': 'blog-163-com-post'})
payload = utils.get_datadic(form)
payload['title'] = src['subject']
payload['HEContent'] = src['content'] + '<wbr>'
payload['allowview'] = '-100'
# print payload
url = 'http://api.blog.163.com/' + username + '/editBlogNew.do?p=1&n=1&from=bloglist'
resp = sess.post(url, data=payload)
logger.info(resp.content)
sfx = re.findall(r'sfx:\'(.*?)\'', resp.content)[0]
if sfx != '/':
blog_url = 'http://' + username + '.blog.163.com/' + sfx
logger.info(' Post OK')
return (blog_url, str(logger))
while sfx == '/' and src['TTL']:
src['TTL'] = src['TTL'] - 1
captcha = sess.get(
'http://api.blog.163.com/cap/captcha.jpgx?parentId=' + parentId +
'&r=308985',
headers={'Accept': config.accept_image})
# 获取验证码字符串
seccode = utils.crack_captcha(captcha.content)
logger.info(' captcha:' + seccode)
payload['valcodeKey'] = seccode
resp = sess.post(url, data=payload)
logger.info(resp.content)
sfx = re.findall(r'sfx:\'(.*?)\'', resp.content)[0]
if sfx != '/':
blog_url = 'http://' + username + '.blog.163.com/' + sfx
logger.info(' Post OK')
return (blog_url, str(logger))
logger.info(' Post Error')
return ('', str(logger))