def __unlock_sogou(self,
url,
resp,
session,
unlock_callback=None,
identify_image_callback=None):
if unlock_callback is None:
unlock_callback = unlock_sogou_callback_example
millis = int(round(time.time() * 1000))
r_captcha = session.get(
'http://weixin.sogou.com/antispider/util/seccode.php?tc={}'.format(
millis))
if not r_captcha.ok:
raise WechatSogouRequestsException('WechatSogouAPI get img', resp)
r_unlock = unlock_callback(url, session, resp, r_captcha.content,
identify_image_callback)
if r_unlock['code'] != 0:
raise WechatSogouVcodeOcrException(
'[WechatSogouAPI identify image] code: {code}, msg: {msg}'.
format(code=r_unlock.get('code'), msg=r_unlock.get('msg')))
else:
self.__set_cache(session.cookies.get('SUID'), r_unlock['id'])
def __unlock_wechat(self,
url,
resp,
session,
unlock_callback=None,
identify_image_callback=None):
if unlock_callback is None:
unlock_callback = unlock_weixin_callback_example
r_captcha = session.get(
'https://mp.weixin.qq.com/mp/verifycode?cert={}'.format(
time.time() * 1000))
if not r_captcha.ok:
raise WechatSogouRequestsException(
'WechatSogouAPI unlock_history get img', resp)
r_unlock = unlock_callback(url, session, resp, r_captcha.content,
identify_image_callback)
if r_unlock['ret'] != 0:
raise WechatSogouVcodeOcrException(
'[WechatSogouAPI identify image] code: {ret}, msg: {errmsg}, cookie_count: {cookie_count}'
.format(ret=r_unlock.get('ret'),
errmsg=r_unlock.get('errmsg'),
cookie_count=r_unlock.get('cookie_count')))
def get_gzh_artilce_by_history(self,
keyword=None,
url=None,
deblocking_callback=None,
identify_image_callback=None):
if url is None:
gzh_list = self.search_gzh(
keyword,
deblocking_callback=deblocking_callback,
identify_image_callback=identify_image_callback)
if gzh_list:
url = gzh_list[0]['url']
else:
raise Exception() # todo use ws exception
req = requests.session()
resp = WechatSogouRequest.get(url,
req=req) # headers=self.__set_cookie()
if not resp.ok:
raise WechatSogouRequestsException(
'WechatSogouAPI get_gzh_artilce_by_history', resp)
if '请输入验证码' in resp.text:
self.__deblocking_history(url, resp, req, deblocking_callback,
identify_image_callback)
resp = WechatSogouRequest.get(
url, req=req) # req=req headers=self.__set_cookie()
return WechatSogouStructuring.get_gzh_info_and_article_by_history(
resp.text)
def get_sugg(self, keyword):
"""获取微信搜狗搜索关键词联想
Parameters
----------
keyword : str or unicode
关键词
Returns
-------
list[str]
联想关键词列表
Raises
------
WechatSogouRequestsException
"""
url = 'http://w.sugg.sogou.com/sugg/ajaj_json.jsp?key={}&type=wxpub&pr=web'.format(
quote(keyword.encode('utf-8')))
r = requests.get(url)
if not r.ok:
raise WechatSogouRequestsException('get_sugg', r)
sugg = re.findall(u'\["' + keyword + '",(.*?),\["', r.text)[0]
return json.loads(sugg)
def __get(self, url, session, headers):
resp = session.get(url, headers=headers, proxies=self.proxies)
if not resp.ok:
raise WechatSogouRequestsException('WechatSogouAPI get error', resp)
return resp
def __get(self, url, session, headers):
resp = session.get(url, headers=headers, **self.requests_kwargs)
if resp.status_code == 302:
resp = session.get(resp.headers['Location'],
headers=headers,
**self.requests_kwargs)
if not resp.ok:
raise WechatSogouRequestsException('WechatSogouAPI get error',
resp)
return resp
def __get(self, url, session, headers):
h = {}
if headers:
for k, v in headers.items():
h[k] = v
if self.headers:
for k, v in self.headers.items():
h[k] = v
resp = session.get(url, headers=h, **self.requests_kwargs)
if not resp.ok:
raise WechatSogouRequestsException('WechatSogouAPI get error', resp)
return resp
def __deblocking_history(self, url, resp, req, deblocking_callback,
identify_image_callback):
r_img = req.get(
'https://mp.weixin.qq.com/mp/verifycode?cert={}'.format(
time.time() * 1000))
if not r_img.ok:
raise WechatSogouRequestsException(
'WechatSogouAPI deblocking_history get img', resp)
if callable(deblocking_callback):
r_deblocking = deblocking_callback(req, resp, r_img.content)
else:
identify_image_callback = identify_image_callback if callable(
identify_image_callback) else identify_image_callback_example
r_deblocking = deblocking_callback_history_example(
url, req, resp, r_img.content, identify_image_callback)
if r_deblocking['ret'] != 0:
raise WechatSogouVcodeOcrException(
'[WechatSogouAPI identify image] code: {ret}, msg: {errmsg}, cookie_count: {cookie_count}'
.format(**r_deblocking))
def __deblocking_search(self, url, resp, req, deblocking_callback,
identify_image_callback):
millis = int(round(time.time() * 1000))
r_img = req.get(
'http://weixin.sogou.com/antispider/util/seccode.php?tc={}'.format(
millis))
if not r_img.ok:
raise WechatSogouRequestsException('WechatSogouAPI get img', resp)
if callable(deblocking_callback):
r_deblocking = deblocking_callback(req, resp, r_img.content)
else:
identify_image_callback = identify_image_callback if callable(
identify_image_callback) else identify_image_callback_example
r_deblocking = deblocking_callback_search_example(
url, req, resp, r_img.content, identify_image_callback)
if r_deblocking['code'] != 0:
raise WechatSogouVcodeOcrException(
'[WechatSogouAPI identify image] code: {code}, msg: {msg}'.
format(**r_deblocking))
else:
self.__set_cache(req.cookies.get('SUID'), r_deblocking['id'])
def search_article(self,
keyword,
page=1,
timesn=0,
article_type=WechatSogouRequest.TYPE_ALL,
ft=None,
et=None,
deblocking_callback=None,
identify_image_callback=None):
"""搜索 文章
对于出现验证码的情况，可以由使用者自己提供：
1、函数 deblocking_callback ，这个函数 handle 出现验证码到解决的整个流程
2、也可以 只提供函数 identify_image_callback，这个函数输入验证码二进制数据，输出验证码文字，剩下的由 wechatsogou 包来解决
注意：
函数 deblocking_callback 和 identify_image_callback 只需要提供一个，如果都提供了，那么 identify_image_callback 不起作用
Parameters
----------
keyword : str or unicode
搜索文字
page : int, optional
页数 the default is 1
timesn : {0, 1, 2, 3, 4, 5}
时间 0 没有限制 / 1一天 / 2一周 / 3一月 / 4一年 / 5自定
the default is 0
article_type : {'image', 'video', 'rich', 'all'}
含有内容的类型 TYPE_IMAGE 有图 / TYPE_VIDEO 有视频 / TYPE_RICH 有图和视频 / TYPE_ALL 啥都有
ft, et : datetime.date or None
当 tsn 是 5 时，ft 代表开始时间，如： 2017-07-01
当 tsn 是 5 时，et 代表结束时间，如： 2017-07-15
deblocking_callback : callable
处理出现验证码页面的函数，参见 deblocking_callback_example
identify_image_callback : callable
处理验证码函数，输入验证码二进制数据，输出文字，参见 identify_image_callback_example
Returns
-------
list[dict]
{
'url': '',
'img': '',
'name': '',
'wechat_id': '',
'post_perm': '',
'qrcode': '',
'introduction': '',
'authentication': ''
}
Raises
------
WechatSogouRequestsException
requests error
"""
req = requests.session()
url = WechatSogouRequest.gen_search_article_url(
keyword,
page,
timesn=timesn,
article_type=article_type,
ft=ft,
et=et)
url_referer = WechatSogouRequest.gen_search_article_url(keyword)
resp = WechatSogouRequest.get(
url, req=req, headers=self.__set_cookie(referer=url_referer))
if not resp.ok:
raise WechatSogouRequestsException('WechatSogouAPI search_article',
resp)
if 'antispider' in resp.url:
self.__deblocking_search(url, resp, req, deblocking_callback,
identify_image_callback)
resp = WechatSogouRequest.get(
url, req=req,
headers=self.__set_cookie(referer=url_referer)) # req=req
return WechatSogouStructuring.get_article_by_search(resp.text)
def search_gzh(self,
keyword,
page=1,
deblocking_callback=None,
identify_image_callback=None):
"""搜索 公众号
对于出现验证码的情况，可以由使用者自己提供：
1、函数 deblocking_callback ，这个函数 handle 出现验证码到解决的整个流程
2、也可以 只提供函数 identify_image_callback，这个函数输入验证码二进制数据，输出验证码文字，剩下的由 wechatsogou 包来解决
注意：
函数 deblocking_callback 和 identify_image_callback 只需要提供一个，如果都提供了，那么 identify_image_callback 不起作用
Parameters
----------
keyword : str or unicode
搜索文字
page : int, optional
页数 the default is 1
deblocking_callback : callable
处理出现验证码页面的函数，参见 deblocking_callback_example
identify_image_callback : callable
处理验证码函数，输入验证码二进制数据，输出文字，参见 identify_image_callback_example
Returns
-------
list[dict]
{
'url': '',
'img': '',
'name': '',
'wechat_id': '',
'post_perm': '',
'qrcode': '',
'introduction': '',
'authentication': ''
}
Raises
------
WechatSogouRequestsException
requests error
"""
req = requests.session()
url = WechatSogouRequest.gen_search_gzh_url(keyword, page)
resp = WechatSogouRequest.get(url,
req=req,
headers=self.__set_cookie())
if not resp.ok:
raise WechatSogouRequestsException('WechatSogouAPI search_gzh',
resp)
if 'antispider' in resp.url:
self.__deblocking_search(url, resp, req, deblocking_callback,
identify_image_callback)
resp = WechatSogouRequest.get(
url, req=req, headers=self.__set_cookie()) # req=req
return WechatSogouStructuring.get_gzh_by_search(resp.text)