def reply_dwnews_news(post_url, src):
s = utils.RAPSession(src)
logger = utils.RAPLogger(post_url)
# Step 1: 登录
if not login_dwnews(s, src):
logger.error(' Login Error')
return (False, str(logger))
logger.info(' Login OK')
r = s.get(post_url)
ikey = re.findall('ikey = "(\w*)"', r.content)[0]
r = s.get('http://blog.dwnews.com/index.php',
params={
'r': 'comment/post',
'callback': 'success_jsonpCallback',
'doitem': 'post',
'content': src['content'],
'type': 'news',
'author': uid,
'url': ikey,
'club_id': '',
'facebook': 0,
'twitter': 0,
'_': str(random.random()),
},
headers={'Referer': post_url})
if 'success' not in r.content:
logger.info('Reply Error')
return (False, str(logger))
logger.info('Reply OK')
return (True, str(logger))
def reply_eulam_forum(post_url, src):
logger = utils.RAPLogger(post_url)
host = utils.get_host(post_url)
s = utils.RAPSession(src)
# Step 1: 登录
if not login_eulam_forum(s, src):
logger.error(' Login Error')
return (False, str(logger))
logger.info(' Login OK')
r = s.get(post_url)
soup = BeautifulSoup(r.content)
form = soup.find('form', attrs={'name': 'form'})
payload = utils.get_datadic(form, CHARSET)
payload['Body'] = src['content'].decode('utf8').encode(CHARSET)
payload['BBSXPCodeForm'] = ''
r = s.post(host + 'ReTopic.asp',
data=payload,
headers={'Referer': post_url})
if u'操作成功'.encode(CHARSET) not in r.content:
logger.error('Reply Error')
return (False, str(logger))
logger.info('Reply OK')
return (True, str(logger))
def post_enewstree_forum(post_url, src):
""" 消息树发主贴函数
@param post_url: 板块地址 如：http://enewstree.com/discuz/forum.php?mod=forumdisplay&fid=47
@type post_url: str
@param src: 用户名，密码，标题，主帖内容，等等。
@type src: dict
@return: 是否发帖成功，帖子URL
@rtype: bool,str
"""
logger = utils.RAPLogger(post_url)
sess = utils.RAPSession(src)
# Step 1: 登录
if not login_enewstree(post_url, sess, src):
logger.error(' Login Error')
return ('', str(logger))
logger.info(' Login OK')
fid = re.findall(r'fid=(\d*)', post_url)[0]
resp = sess.get('http://enewstree.com/discuz/forum.php?mod=post&action=newthread&fid='+fid)
formhash = re.findall(r'formhash=(.*?)"', resp.content)[0]
logger.info('formhash:'+ formhash)
payload = {
'formhash':formhash,
'posttime':int(time.time()),
'wysiwyg':'1',
'subject':src['subject'].decode('utf8').encode(CHARSET,'ignore'),
'message':src['content'].decode('utf8').encode(CHARSET,'ignore'),
'allownoticeauthor':'1',
'usesig':'1',
'secqaahash':'qSxqZkkW',
'secanswer':'1776',
'seccodehash':'cSxqZkkW',
'seccodemodid':'forum::post',
'seccodeverify':'ec48',
'save':'',
'uploadalbum':'-2',
'newalbum':'',
}
# 发送登录post包
resp = sess.post('http://enewstree.com/discuz/forum.php?mod=post&action=newthread&fid='+fid
+'&extra=&topicsubmit=yes',
data=payload,
headers = {
'Referer':post_url
})
utils.print_to_file(resp.content)
# 若指定字样出现在response中，表示回复成功
if src['subject'].decode('utf8') not in resp.content.decode(CHARSET):
logger.error(' Post Error')
return ('', str(logger))
logger.info(' Post OK')
url = resp.url
print url
return (url, str(logger))
def reply_sina_news(post_url, src):
""" 新浪新闻回复函数
- Name: 新浪新闻
- Feature: ^http://[^(c|f)].*.sina.com.cn
- Captcha: YES
- Login: YES
@param post_url: 新浪地址
@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)
resp = sess.get(post_url)
# 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
# 频道id
channel = re.findall(r'channel:.*\'(.*?)\'', resp.content)[0]
# 新闻id
newsid = re.findall(r'newsid:.*\'(.*?)\'', resp.content)[0]
# 构造回复参数
payload = {
'channel': channel,
'newsid': newsid,
'parent': 'B',
'content': src['content'].decode('utf-8').encode(CHARSET),
'format': 'js',
'ie': CHARSET,
'oe': CHARSET,
'ispost': 0,
'share_url': post_url,
'video_url': '',
'img_url': ''
}
# 回复地址
reply_url = 'http://comment5.news.sina.com.cn/cmnt/submit'
# 发送回复post包
resp = sess.post(reply_url, data=payload, headers={'Referer': post_url})
# 若指定字样出现在response中，表示回复成功
if 'result' not in resp.content:
logger.error(' Reply Error')
return (False, str(logger))
logger.info(' Reply OK')
return (True, str(logger))
def post_sohu_blog(post_url, src):
""" 搜狐博客发帖函数
@param post_url: 搜狐地址
@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_sohu(sess, post_url, src):
logger.error(' Login Error')
return (False, str(logger))
logger.info(' Login OK')
# Step 2: 回复
payload = {
'oper': 'art_ok',
'm': 'save',
'shortcutFlag': '',
'contrChId': '',
'contrCataId': '',
'subflag': 0,
'entrytitle': src['subject'].decode('utf-8').encode('gbk'),
'keywords': src['subject'].decode('utf-8').encode('gbk'),
'categoryId': 0,
'newGategory': '',
'vc': '',
'entrycontent': src['content'].decode('utf-8').encode('gbk'),
'excerpt': '',
'allowComment': 2,
'perm': 0,
'postToGroup': 'off'
}
reply_url = 'http://blog.sohu.com/manage/entry.do'
headers = {
'Host': 'blog.sohu.com',
'Origin': 'http://blog.sohu.com',
'Referer': 'http://blog.sohu.com/manage/entry.do?m=add&t=shortcut',
'User-Agent': config.user_agent
}
resp = sess.post(reply_url, data=payload, headers=headers)
logger.info(' info: ' + resp.url)
if u'秒钟后自动'.encode('gbk') not in resp.content:
logger.error(' Post Error')
return ('', str(logger))
resp = sess.post('http://blog.sohu.com/home/entry/list.htm')
blogId = re.findall(r'data-blogid="(\d+)"', resp.content)[0]
logger.info(' Post OK')
return ('http://bigdatabigbai.blog.sohu.com/' + blogId + '.html',
str(logger))
def thumb_up_163(post_url, src):
logger = utils.RAPLogger(post_url)
sess = utils.RAPSession(src)
resp = sess.get(post_url)
resp = sess.post(src['extra']['target_url'],
headers={
'Referer': post_url,
'Host': utils.get_host(post_url),
'X-Requested-With': 'XMLHttpRequest',
})
logger.info(resp.content)
return (True, str(logger))
def reply_backchina_forum(post_url, src):
"""倍可亲回复模块
@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
"""
# Returnable logger
logger = utils.RAPLogger(post_url)
host = utils.get_host(post_url)
sess = utils.RAPSession(src)
# Step 1: 登录
if not login_backchina(sess, src):
logger.error(' Login Error')
return (False, str(logger))
logger.info(' Login OK')
# Step 2: Load post page
# 获取所需发帖页面，查找与{'id':'fastpostform'}匹配的form标签
resp = sess.get(post_url)
soup = BeautifulSoup(resp.content)
form = soup.find('form', attrs={'id': 'fastpostform'})
# Step 3: Submit
# 回复内容
payload = utils.get_datadic(form)
if 'subject' in src:
payload['subject'] = src['subject']
payload['message'] = src['content']
#发送post包
resp = sess.post(host + form['action'], data=payload)
#判断回帖后页面是否含有回帖内容，若存在则证明回帖成功，否则失败
if src['content'] in resp.content:
logger.info('Reply OK')
else:
logger.error('Reply Error: Reply Error, please try again !')
return (False, str(logger))
return (True, str(logger))
def post_wailaike_forum(post_url, src):
""" 外来客论坛发主贴函数
@param post_url: 板块地址 如：http://www.wailaike.net/group_post?gid=1
@type post_url: str
@param src: 用户名，密码，标题，主帖内容，等等。用户名：[email protected] 密码：wenshen4921119
@type src: dict
@return: 是否发帖成功，帖子URL
@rtype: bool,str
"""
# Returnable logger
logger = utils.RAPLogger(post_url)
host = utils.get_host(post_url)
sess = utils.RAPSession(src)
# Step 1: 登录
if not login_wailaike(sess, src):
logger.error(' Login Error')
return ('', str(logger))
logger.info(' Login OK')
gid = re.findall(r'gid=(\d*)', post_url)[0]
resp = sess.get('http://www.wailaike.net/newpost?gid='+gid)
soup = BeautifulSoup(resp.content)
# 获得发帖form
form = soup.find('form', attrs={'id': 'editor'})
# 构造回复参数
payload = utils.get_datadic(form)
payload['title'] = src['subject'].decode('utf8').encode(CHARSET)
payload['rstbody'] = src['content'].decode('utf8').encode(CHARSET)
resp = sess.get('http://www.wailaike.net/time.php')
payload['time'] = re.findall('"time":"(.*?)"', resp.content)[0]
# 发送发帖post包
resp = sess.post('http://www.wailaike.net/newpost?gid='+gid, data=payload)
# By sniper 2015-2-1
# 标题中的'('和')'等需要在正则表达式中转义
# 如：[转帖]ZT) 汉服是FQ闹的大笑话
subject = re.escape(src['subject'])
url = re.findall(r'<h3 class="titles-txt"><a href=\"(.*?)\" target="_blank">' + subject + '</a></h3>',resp.content)[0]
url = "http://www.wailaike.net" + url
# 如果url未成功匹配，则抛出异常，Post Error
logger.info(' Post OK')
return (url, str(logger))
def post_powerapple_forum(post_url, src):
""" 超级苹果论坛发主贴函数
@param post_url: 板块地址 如：http://bbs.powerapple.com/forum.php?mod=forumdisplay&fid=50
@type post_url: str
@param src: 用户名，密码，标题，主帖内容，等等。
@type src: dict
@return: 是否发帖成功，帖子URL
@rtype: bool,str
"""
logger = utils.RAPLogger(post_url)
host = utils.get_host(post_url)
sess = utils.RAPSession(src)
# Step 1: 登录
if not login_powerapple(sess, src):
logger.error(' Login Error')
return ('', str(logger))
logger.info(' Login OK')
# Step 2: Load post page
fid = re.findall(r'fid=(\d+)', post_url)[0]
# 获取所需发帖页面，查找与{'id':'fastpostform'}匹配的form标签
resp = sess.get(
'http://bbs.powerapple.com/forum.php?mod=post&action=newthread&fid=' +
fid)
soup = BeautifulSoup(resp.content)
form = soup.find('form', attrs={'id': 'postform'})
# Step 3: Submit
# 回复内容
payload = get_datadic(form)
payload['subject'] = src['subject']
payload['message'] = src['content']
payload['typeid'] = '138'
#发送post包
resp = sess.post(host + form['action'], data=payload)
#获取回帖页面content的HTML
print_to_file(resp.content)
#判断回帖后页面是否含有回帖内容，若存在则证明回帖成功，否则失败
if src['subject'] in resp.content:
logger.info('Post OK')
else:
logger.error('Reply Error: please try again !')
return ('', str(logger))
return (resp.url, str(logger))
def thumb_up_qq(post_url, src):
logger = utils.RAPLogger(post_url)
sess = utils.RAPSession(src)
resp = sess.get(src['extra']['target_url'],
headers={'Referer': post_url},
params={
'targetid': post_url.split('/')[-1],
'callback': 'ding',
})
logger.info(resp.content)
if 'Operation too frequent' in resp.content:
logger.info('Operation too frequent')
return (False, str(logger))
return (True, str(logger))
def thumb_up_sohu(post_url, src):
logger = utils.RAPLogger(post_url)
sess = utils.RAPSession(src)
resp = sess.get('http://changyan.sohu.com/api/2/comment/action',
headers={'Referer': post_url},
params={
'callback': 'fn',
'action_type': 1,
'comment_id': src['extra']['comment_id'],
'client_id': post_url.split('/')[4],
'topic_id': src['extra']['topic_id'],
'_': int(time.time() * 1000),
})
logger.info(resp.content)
return (True, str(logger))
def post_kdnet(post_url, src):
""" 凯迪社区发主贴函数
- Name: 凯迪社区
- Feature: club.kdnet.net
- Captcha: NO
- Login: NO
@param post_url: 板块地址 如：http://club.kdnet.net/list.asp?boardid=2
@type post_url: str
@param src: 用户名，密码，标题，主帖内容，等等。
@type src: dict
@return: 是否发帖成功，帖子URL
@rtype: bool,str
"""
logger = utils.RAPLogger(post_url)
sess = utils.RAPSession(src)
# Step 1: 登录
if not login_kdnet(sess, src):
logger.error(' Login Error')
return ('', str(logger))
logger.info(' Login OK')
# 获得boardid，作为post参数
boardid = re.findall(r'boardid=(\d*)',post_url)[0]
resp = sess.get('http://upfile1.kdnet.net/textareaeditor/post_ubb.asp?action=new&boardid='+boardid)
soup = BeautifulSoup(resp.content)
# 获得发帖form
form = soup.find('form', attrs={'id': 'Dvform'})
# 构造回复参数
payload = utils.get_datadic(form)
payload['topic'] = src['subject'].decode('utf8').encode(CHARSET,'ignore')
payload['body'] = src['content'].decode('utf8').encode(CHARSET,'ignore')
payload['font1'] = u'[原创]'.encode(CHARSET,'ignore')
# 发送发帖post包
resp = sess.post('http://upfile1.kdnet.net/SavePost_ubb.asp?Action=snew&boardid=' + boardid, data=payload)
# 若指定字样出现在response中，表示发帖成功
if u'发帖成功'.encode(CHARSET,'ignore') not in resp.content:
logger.error(' Post Error')
return ('', str(logger))
logger.info(' Post OK')
url = re.findall(r'var url="(.*?)"',resp.content)[0]
print url
return (url, str(logger))
def reply_kdnet(post_url, src):
""" 凯迪社区回复函数
- Name: 凯迪社区
- Feature: club.kdnet.net
- Captcha: NO
- 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)
resp = sess.get(post_url)
post_url = resp.url
# 获得回复iframe
iframe = re.findall('<iframe src=\"(.*?)\"', resp.content)[0]
resp = sess.get(iframe.decode(CHARSET))
soup = BeautifulSoup(resp.content)
# 获得回复form
form = soup.find('form', attrs={'id': 't_form'})
# 获得boardid，作为post参数
boardid = re.findall(r'boardid=(.*\d)', post_url)[0]
# 构造回复参数
payload = utils.get_datadic(form)
payload['UserName'] = src['username'].decode('utf8').encode(CHARSET,'ignore')
payload['password'] = src['password'].decode('utf8').encode(CHARSET,'ignore')
payload['body'] = src['content'].decode('utf8').encode(CHARSET,'ignore')
# 回复地址
reply_url = 'http://upfile1.kdnet.net/do_lu_shuiyin.asp?'\
+ 'action=sre&method=fastreply&BoardID='
# 发送回复post包
resp = sess.post(reply_url + boardid, data=payload)
print resp.content.decode(CHARSET)
# 若指定字样出现在response中，表示回复成功
if u'成功回复'.encode(CHARSET,'ignore') not in resp.content:
logger.error(' Reply Error')
return (False, str(logger))
logger.info(' Reply OK')
return (True, str(logger))
def post_backchina_forum(post_url, src):
""" 倍可亲论坛发主贴函数
@param post_url: 板块地址 如：http://www.backchina.com/forum/37/index-1.html
@type post_url: str
@param src: 用户名，密码，标题，主帖内容，等等。
@type src: dict
@return: 是否发帖成功，帖子URL
@rtype: bool,str
"""
# Returnable logger
logger = utils.RAPLogger(post_url)
sess = utils.RAPSession(src)
# Step 1: 登录
if not login_backchina(sess, src):
logger.error(' Login Error')
return ('', str(logger))
logger.info(' Login OK')
fid = re.findall(r'forum/(\d+)/', post_url)[0]
resp = sess.get(
'http://www.backchina.com/forum.php?mod=post&action=newthread&fid=' +
fid)
soup = BeautifulSoup(resp.content)
# 获得发帖form
form = soup.find('form', attrs={'id': 'postform'})
# 构造回复参数
payload = utils.get_datadic(form)
payload['subject'] = src['subject']
payload['message'] = src['content']
# 发送发帖post包
resp = sess.post(
'http://www.backchina.com/forum.php?mod=post&action=newthread&fid=' +
fid + '&extra=&topicsubmit=yes',
data=payload)
# 若指定字样出现在response中，表示发帖成功
if src['subject'] not in resp.content:
logger.error(' Post Error')
return ('', str(logger))
logger.info(' Post OK')
url = resp.url
return (url, str(logger))
def upload_head_backchina_forum(src):
logger = utils.RAPLogger('Upload head 51_forum=>' + src['username'])
sess = utils.RAPSession(src)
# Step 1: 登录
if not login_backchina(sess, src):
logger.error('Login Error')
return ('', str(logger))
logger.info('Login OK')
resp = sess.get('http://www.backchina.com/home.php?mod=spacecp&ac=avatar')
input = urllib.unquote(re.findall(r'input=(.*?)&', resp.content)[0])
agent = re.findall(r'agent=(.*?)&', resp.content)[0]
head_url = re.findall(r'<td><img src="(.*?)"', resp.content)[0]
print 'input:', input
print 'agent:', agent
avatar1 = binascii.hexlify(open(src['head'], 'rb').read()).upper()
avatar2 = avatar1
avatar3 = avatar1
params = {
'm': 'user',
'inajax': '1',
'a': 'rectavatar',
'appid': '14',
'input': input,
'agent': agent,
'avatartype': 'virtual'
}
payload = {
'avatar1': avatar1,
'avatar2': avatar2,
'avatar3': avatar3,
'urlReaderTS': str(time.time() * 1000)
}
resp = sess.post('http://backchina-member.com/ucenter/index.php',
data=payload,
params=params)
print resp.content
if 'success="1"' in resp.content:
logger.info('uploadavatar OK')
return (head_url, str(logger))
else:
logger.info('uploadavatar Error')
return ('', str(logger))
def post_creaders_forum(post_url, src):
"""万维论坛发主贴模块
@param sess: requests.Session()
@type sess: Session
@param post_url: 帖子地址 如：http://bbs.creaders.net/life/
@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
"""
logger = utils.RAPLogger(post_url)
sess = utils.RAPSession(src)
url = post_url.rpartition('/')[0] + '/'
resp = sess.get(url + 'post.php?')
# 构造回复参数
payload = {
'user_name2': src['username'].decode('utf8').encode(CHARSET, 'ignore'),
'user_password2':
src['password'].decode('utf8').encode(CHARSET, 'ignore'),
'captcha': '',
'trd_subject': src['subject'].decode('utf8').encode(CHARSET, 'ignore'),
'trd_content': src['content'].decode('utf8').encode(CHARSET, 'ignore')
}
# 发送发主贴post包
# print url+'post.php'
resp = sess.post(url + 'post.php', data=payload)
content = resp.content.decode(CHARSET, 'ignore')
# utils.print_to_file(resp.content)
# By sniper 2015-2-1
# 标题中的'('和')'等需要在正则表达式中转义
# 如：[转帖]ZT) 汉服是FQ闹的大笑话
subject = re.escape(src['subject'].decode('utf8'))
href = re.findall(r'<a href=\'(.*?)\' class=\'thread_title\'>' + subject,
content)[0]
url = post_url + href
# 如果url未成功匹配，则抛出异常，Post Error
logger.info('Post OK')
return (url, str(logger))
def reply_enewstree_forum(post_url, src):
""" 消息树回复函数
- Name: 凯迪社区
- Feature: club.kdnet.net
- Captcha: NO
- Login: NO
@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_enewstree(post_url, sess, src):
logger.error(' Login Error')
return ('', str(logger))
logger.info(' Login OK')
resp = sess.get(post_url)
soup = BeautifulSoup(resp.content)
# 获得回复form
form = soup.find('form', attrs={'id': 'fastpostform'})
# 构造回复参数
payload = utils.get_datadic(form)
payload['message'] = src['content'].decode('utf8').encode(CHARSET,'ignore'),
resp = sess.post('http://enewstree.com/discuz/'+form['action'],
data=payload,
headers = {
'Referer':post_url
})
if src['content'].decode('utf8') not in resp.content.decode(CHARSET,'ignore'):
logger.error(' Reply Error')
return (False, str(logger))
logger.info(' Reply OK')
return (True, str(logger))
def post_1dpw_forum(post_url, src):
""" 加国华人网发主贴函数
@param post_url: 板块地址 如：http://bbs.1dpw.com/forum-71-1.html
@type post_url: str
@param src: 用户名，密码，标题，主帖内容，等等。
@type src: dict
@return: 是否发帖成功，帖子URL
@rtype: bool,str
"""
host = utils.get_host(post_url)
logger = utils.RAPLogger(post_url)
sess = utils.RAPSession(src)
# Step 1: 登录
if not login_1dpw(post_url, sess, src):
logger.error(' Login Error')
return ('', str(logger))
logger.info(' Login OK')
resp = sess.get(post_url)
soup = BeautifulSoup(resp.content)
# 获得回复form
form = soup.find('form', attrs={'id': 'fastpostform'})
# 构造回复参数
payload = utils.get_datadic(form)
payload['subject'] = src['subject']
payload['message'] = src['content']
payload['posttime'] = int(time.time())
# 发送登录post包
resp = sess.post(host + form['action'] + '&inajax=1', data=payload)
# 若指定字样出现在response中，表示发帖成功
if '主题已发布' not in resp.content:
logger.error(' Post Error')
return ('', str(logger))
logger.info(' Post OK')
url = host + re.findall(r'succeedhandle_fastnewpost\(\'(.*?)\'', resp.content)[0]
print url
return (url, str(logger))
def thumb_up_dwnews(post_url, src={}):
logger = utils.RAPLogger(post_url)
sess = utils.RAPSession(src)
resp = sess.get('http://blog.dwnews.com/index.php',
params={
'r':
'club/clubzan',
'id':
re.findall('(\d+)', post_url)[0],
'type':
'nolikes' if src['extra']['like'] == 'false'
or src['extra']['like'] == 'False' else 'likes',
'callback':
'?',
})
logger.info(resp.content)
if 'success' not in resp.content:
logger.error('Thumb Up Error')
return (False, str(logger))
logger.info('Thumb Up OK')
return (True, str(logger))
def reply_unitedtimes(post_url, src):
""" 澳洲联合网回复函数
- Name: 澳洲联合网
- Feature: unitedtimes.com.au/
- Captcha: NO
- Login: NO
@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)
resp = sess.get(post_url)
# 获得回复iframe
iframe = re.findall('<iframe src=\"(.*?)\"', resp.content)[0]
resp = sess.get(iframe.decode(CHARSET))
soup = BeautifulSoup(resp.content)
# 获得回复form
form = soup.find('form', attrs={'method': 'post'})
# 构造回复参数
payload = utils.get_datadic(form)
payload['content'] = src['content']
# 发送回复post包
resp = sess.post(form['action'], data=payload)
# 若指定字样出现在response中，表示回复成功
if '操作成功' not in resp.content:
logger.error(' Reply Error')
return (False, str(logger))
logger.info(' Reply OK')
return (True, str(logger))
def reply_creaders_news(post_url, src):
logger = utils.RAPLogger(post_url)
host = utils.get_host(post_url)
s = utils.RAPSession(src)
r = s.get(post_url)
payload = {
'news_id': re.findall('news_id=(\d+)', r.content)[0],
'r_nid': re.findall('r_nid=(\d+)', r.content)[0],
'username': src['username'],
'password': src['password'],
'replyid': 0,
# The charset of this page is `gb2312` absolutely, but it seems that
# `saytext` receives `utf8` only.
'saytext': src['content'],
}
r = s.post(host + '/headline/postcomment.php', data=payload)
if u'评论成功'.encode('gb2312') not in r.content:
logger.error('Reply Error')
return (False, str(logger))
logger.info('Reply OK')
return (True, str(logger))
def reply_penchinese_blog(post_url, src):
""" 独立中文笔会博客回复函数
- Name: 独立中文笔会
- Feature: club.kdnet.net
- Captcha: NO
- 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)
resp = sess.get(post_url)
soup = BeautifulSoup(resp.content)
# 获得回复form
form = soup.find('form', attrs={'id': 'commentform'})
# 构造回复参数
payload = utils.get_datadic(form)
payload['author'] = src['username']
payload['email'] = src['password']
payload['comment'] = src['content']
# 发送回复post包
resp = sess.post(form['action'], data=payload)
print resp.url
# 若指定字样出现在response中，表示回复成功
if resp.url == form['action']:
logger.error(' Reply Error')
return (False, str(logger))
logger.info(' Reply OK')
return (True, str(logger))
def reply_creaders_forum(post_url, src):
"""万维论坛回复模块
@author: sky
@since: 2014-11-27
@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
"""
logger = utils.RAPLogger(post_url)
sess = utils.RAPSession(src)
# step 2: 获取回帖页面
resp = sess.get(post_url)
# step 3: 提交回帖
# 回复内容
payload = {
'user_name2': src['username'].decode('utf8').encode(CHARSET),
'user_password2': src['password'].decode('utf8').encode(CHARSET),
'captcha': '',
'btrd_subject': src['content'].decode('utf8').encode(CHARSET),
'btrd_content': src['content'].decode('utf8').encode(CHARSET)
}
# 发送post包
resp = sess.post(post_url, data=payload)
#判断回帖后页面是否含有回帖内容，若存在则证明回帖成功，否则失败
if src['content'].decode('utf8').encode(CHARSET) in resp.content:
logger.info('Reply OK')
else:
logger.error('Reply Error')
return (False, str(logger))
return (True, str(logger))
def reply_1dpw_forum(post_url, src):
""" 加国华人网发回复函数（10个字符）
@param post_url: 帖子地址
@type post_url: str
@param src: 用户名，密码，内容，等等。
@type src: dict
@return: 是否回复成功
@rtype: bool
"""
host = utils.get_host(post_url)
logger = utils.RAPLogger(post_url)
sess = utils.RAPSession(src)
# Step 1: 登录
if not login_1dpw(post_url, sess, src):
logger.error(' Login Error')
return (False, str(logger))
logger.info(' Login OK')
resp = sess.get(post_url)
soup = BeautifulSoup(resp.content)
# 获得回复form
form = soup.find('form', attrs={'id': 'fastpostform'})
# 构造回复参数
payload = utils.get_datadic(form)
payload['message'] = src['content']
payload['posttime'] = int(time.time())
# 发送登录post包
resp = sess.post(host + form['action'] + '&inajax=1', data=payload)
# 若指定字样出现在response中，表示发帖成功
if 'Database' not in resp.content:
logger.error(' Reply Error')
return (False, str(logger))
logger.info(' Reply OK')
return (True, str(logger))
def reply_powerapple_forum(post_url, src):
# Returnable logger
logger = utils.RAPLogger(post_url)
host = utils.get_host(post_url)
sess = utils.RAPSession(src)
# Step 1: 登录
if not login_powerapple(sess, src):
logger.error(' Login Error')
return (False, str(logger))
logger.info(' Login OK')
# Step 2: Load post page
# 获取所需发帖页面，查找与{'id':'fastpostform'}匹配的form标签
resp = sess.get(post_url)
soup = BeautifulSoup(resp.content)
form = soup.find('form', attrs={'id': 'fastpostform'})
# Step 3: Submit
# 回复内容
payload = get_datadic(form)
if 'subject' in src:
payload['subject'] = src['subject']
payload['message'] = src['content']
#发送post包
resp = sess.post(host + form['action'], data=payload)
#获取回帖页面content的HTML
soup = BeautifulSoup(resp.content)
#判断回帖后页面是否含有回帖内容，若存在则证明回帖成功，否则失败
if src['content'] in resp.content:
logger.info('Reply OK')
else:
logger.error('Reply Error: please try again !')
return (False, str(logger))
return (True, str(logger))
def get_account_info_dwnews_blog(src):
""" 多维账户信息获取函数
@param src: 用户名，密码
@type src: dict
@return: 账户信息
@rtype: dict
"""
logger = utils.RAPLogger(src['username'])
sess = utils.RAPSession(src)
# Step 1: 登录
if not login_dwnews(sess, src):
logger.error(' Login Error')
return ({}, str(logger))
logger.info(' Login OK')
resp = sess.get('http://blog.dwnews.com/myinfo.html')
soup = BeautifulSoup(resp.content)
head_image = soup.select('div.portrait img')[0]['src']
account_score = ''
account_class = ''
time_register = re.findall(r'注册时间:(.*?)</div>', resp.content)[0]
time_last_login = re.findall(r'上次登录时间：(.*?) </div>', resp.content)[0]
login_count = ''
count_post = re.findall(r'文章<span>\((\d+)\)</span>', resp.content)[0]
count_reply = re.findall(r'评论<span>\((\d+)\)</span>', resp.content)[0]
account_info = {
#########################################
# 用户名
'username': src['username'],
# 密码
'password': src['password'],
# 头像图片
'head_image': head_image,
#########################################
# 积分
'account_score': account_score,
# 等级
'account_class': account_class,
#########################################
# 注册时间
'time_register': time_register,
# 最近登录时间
'time_last_login': time_last_login,
# 登录次数
'login_count': login_count,
#########################################
# 主帖数
'count_post': count_post,
# 回复数
'count_reply': count_reply
#########################################
}
logger.info('Get account info OK')
return (account_info, str(logger))
def post_dwnews_blog(post_url, src):
""" 多维社区发主贴函数
- Name: 多维社区
- Feature: http://blog.dwnews.com/
- Captcha: NO
- Login: NO
@param post_url: 板块地址 如：http://blog.dwnews.com/
@type post_url: str
@param src: 用户名，密码，标题，主帖内容，等等。
@type src: dict
@return: 是否发帖成功，帖子URL
@rtype: bool,str
"""
logger = utils.RAPLogger(post_url)
sess = utils.RAPSession(src)
# Step 1: 登录
if not login_dwnews(sess, src):
logger.error(' Login Error')
return ('', str(logger))
logger.info(' Login OK')
# Step 2: 验证用户，取得Token
resp = sess.get(
'http://blog.dwnews.com/index.php?r=user/checkMember&callback=?')
csrf_token = re.findall(r'"CsrfToken":"(.*?)"',
resp.content)[0].replace('\\', '')
logger.info('csrf_token: ' + csrf_token)
# 回复
payload = {
'title': src['subject'],
'content': '<p>' + src['content'] + '</p>',
'tag': '时事',
'catid': '5',
'facebook': '0',
'twitter': '0',
'linkedin': '0',
'google': '0',
'CsrfToken': csrf_token
}
resp = sess.post('http://blog.dwnews.com/index.php?r=club/post',
data=payload,
headers={
'Accept':
'application/json, text/javascript, */*; q=0.01',
'Referer': 'http://blog.dwnews.com/mytopic',
'X-Requested-With': 'XMLHttpRequest',
})
# 若指定字样出现在response中，表示发帖成功
if 'success' not in resp.content:
logger.info(resp.content)
logger.error(' Post Error')
return ('', str(logger))
resp = sess.get('http://blog.dwnews.com/index.php?r=club/makehtml&catid=5')
if 'ok' not in resp.content:
logger.info(resp.content)
logger.error(' Post Error')
return ('', str(logger))
logger.info(' Post OK')
resp = sess.get('http://blog.dwnews.com/mytopic')
soup = BeautifulSoup(resp.content)
url = soup.select('div.loadMore li a[href^="http"]')[0]['href']
return (url, str(logger))
def get_account_info_eulam_forum(src):
""" 欧浪账户信息获取函数
@param src: 用户名，密码
@type src: dict
@return: 账户信息
@rtype: dict
"""
logger = utils.RAPLogger(src['username'])
sess = utils.RAPSession(src)
# Step 1: 登录
if not login_eulam_forum(sess, src):
logger.error(' Login Error')
return ({}, str(logger))
logger.info(' Login OK')
resp = sess.get('http://bbs.eulam.com/user/Profile.asp?UserName='******'username'])
head_image = 'http://bbs.eulam.com/css/css1/images/photobg.gif'
html = resp.content.decode(CHARSET, 'ignore').encode('utf8')
account_score = re.findall(r'<li>用户魅力：(\d+)</li>', html)[0]
account_class = re.findall(r'<li>用户角色：(.*?)</li>', html)[0]
time_register = re.findall(r'<li>注册时间：(.*?)</li>', html)[0]
year = time.strftime('%Y', time.localtime(time.time()))
time_last_login = year + '-' + re.findall(r'<li>上次登录：(.*?)</li>', html)[0]
login_count = re.findall(r'<li>登录次数：(\d+)</li>', html)[0]
count_post = re.findall(r'<li>发表原贴：(\d+)</li>', html)[0]
count_reply = re.findall(r'<li>发表回贴：(\d+)</li>', html)[0]
account_info = {
#########################################
# 用户名
'username': src['username'],
# 密码
'password': src['password'],
# 头像图片
'head_image': head_image,
#########################################
# 积分
'account_score': account_score,
# 等级
'account_class': account_class,
#########################################
# 注册时间
'time_register': time_register,
# 最近登录时间
'time_last_login': time_last_login,
# 登录次数
'login_count': login_count,
#########################################
# 主帖数
'count_post': count_post,
# 回复数
'count_reply': count_reply
#########################################
}
logger.info('Get account info OK')
return (account_info, str(logger))
def get_account_info_sina_club(src):
""" 新浪账户信息获取函数
@param src: 用户名，密码
@type src: dict
@return: 账户信息
@rtype: dict
"""
logger = utils.RAPLogger(src['username'])
sess = utils.RAPSession(src)
# Step 1: 登录
if not login_sina(sess, src):
logger.error(' Login Error')
return ({}, str(logger))
logger.info(' Login OK')
resp = sess.get('http://club.mil.news.sina.com.cn/memcp.php')
soup = BeautifulSoup(resp.content)
head_image = soup.select('div.avatar img')[0]['src']
html = resp.content.decode(CHARSET).encode('utf8')
account_score = re.findall(r'<li>积分: (\d+)</li>', html)[0]
account_class = re.findall(
r'<label>用户组:</label> <font color="green">(.*?)</font>', html)[0]
time_register = re.findall(r'<label>注册日期:</label>(.*?)</li>', html)[0]
time_last_login = re.findall(r'<label>上次访问:</label>(.*?)</li>', html)[0]
login_count = ''
count_post = re.findall(r'<li>帖子: (\d+)', html)[0]
count_reply = re.findall(r'<li>精华: (\d+)', html)[0]
account_info = {
#########################################
# 用户名
'username': src['username'],
# 密码
'password': src['password'],
# 头像图片
'head_image': head_image,
#########################################
# 积分
'account_score': account_score,
# 等级
'account_class': account_class,
#########################################
# 注册时间
'time_register': time_register,
# 最近登录时间
'time_last_login': time_last_login,
# 登录次数
'login_count': login_count,
#########################################
# 主帖数
'count_post': count_post,
# 回复数
'count_reply': count_reply
#########################################
}
logger.info('Get account info OK')
return (account_info, str(logger))
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))
