def __search_book_html(self, anywords, page): """ 检索图书列表页面 :param anywords: 关键字 :param page: 页码 :return: html code """ _params = { "dt": "ALL", "cl": "ALL", "dp": "20", "sf": "M_PUB_YEAR", "ob": "DESC", "sm": "table", "dept": "ALL", "ecx": "0", "anywords": "", # not anywords.. "page": 1, } _headers = { "Host": "lib.wyu.edu.cn", "Referer": "http://lib.wyu.edu.cn/opac/search.aspx", "Accept-Language": ":zh-CN,zh;q=0.8,en;q=0.6,zh-TW;q=0.4", } # url要对中文编码.. _params["anywords"] = anywords.decode("utf-8").encode("gbk") _params["page"] = page r = requests.get(url=WyuLibrary.url_search, headers=_headers, params=_params, timeout=self._timeout) # _.d(r.content.decode(_.get_charset(r.content))) return r.content.decode(_.get_charset(r.content))
def __get_score_html(self): self._headers['Referer'] = 'http://jwc.wyu.edu.cn/student/menu.asp' r = requests.get('http://jwc.wyu.edu.cn/student/f4_myscore11.asp', headers=self._headers, allow_redirects=False, cookies=self._cookies) return r.content.decode(_.get_charset(r.content))
def __search_book_html(self, anywords, page): """ 检索图书列表页面 :param anywords: 关键字 :param page: 页码 :return: html code """ _params = { 'dt': 'ALL', 'cl': 'ALL', 'dp': '20', 'sf': 'M_PUB_YEAR', 'ob': 'DESC', 'sm': 'table', 'dept': 'ALL', 'ecx': '0', 'anywords': '', # not anywords.. 'page': 1 } _headers = { 'Host': 'lib.wyu.edu.cn', 'Referer': 'http://lib.wyu.edu.cn/opac/search.aspx', 'Accept-Language': ':zh-CN,zh;q=0.8,en;q=0.6,zh-TW;q=0.4' } # url要对中文编码.. _params['anywords'] = anywords.decode('utf-8').encode('gbk') _params['page'] = page r = requests.get(url=WyuLibrary.url_search, headers=_headers, params=_params, timeout=self._timeout) # _.d(r.content.decode(_.get_charset(r.content))) return r.content.decode(_.get_charset(r.content))
def __get_course_html(self): """ 获得课表页面 :return: 已转码的html """ self._headers['Referer'] = 'http://jwc.wyu.edu.cn/student/menu.asp' r = requests.get('http://jwc.wyu.edu.cn/student/f3.asp', headers=self._headers, cookies=self._cookies) return r.content.decode(_.get_charset(r.content))
def __wyu_news_content(url): r = requests.get(url) encoding = _.get_charset(r.content) try: return r.content.decode(encoding) except Exception as e: # gb2312不行就换成gbk尝试 if encoding != 'gbk': return r.content.decode('gbk') return r.content
def _get_electricity_info_html( apart_id, meter_room): """get html :param apart_id: 栋数 :param meter_room: 宿舍号 """ if apart.get(apart_id) is None: raise KeyError('not support the apart_id= ' + apart_id) post_data = { 'action': 'search', 'apartID': apart.get(apart_id), 'meter_room': apart_id + meter_room } r = requests.post('http://202.192.252.140/index.asp', data=post_data) return r.content.decode(_.get_charset(r.content))
def __book_status_html(self, ctrlno): """ 获取图书借阅页面 :param ctrlno: :return: """ _params = {"ctrlno": ctrlno} _headers = { "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8", "Accept-Encoding": "gzip, deflate, sdch", "Accept-Language": "zh-CN,zh;q=0.8,en;q=0.6,zh-TW;q=0.4", "Host": "lib.wyu.edu.cn", "Referer": "http://lib.wyu.edu.cn/opac/searchresult.aspx", } r = requests.get(url=WyuLibrary.url_book_info, headers=_headers, params=_params, timeout=self._timeout) # _.d(r.content.decode(_.get_charset(r.content))) return r.content.decode(_.get_charset(r.content))
def __book_status_html(self, ctrlno): """ 获取图书借阅页面 :param ctrlno: :return: """ _params = {'ctrlno': ctrlno} _headers = { 'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8', 'Accept-Encoding': 'gzip, deflate, sdch', 'Accept-Language': 'zh-CN,zh;q=0.8,en;q=0.6,zh-TW;q=0.4', 'Host': 'lib.wyu.edu.cn', 'Referer': 'http://lib.wyu.edu.cn/opac/searchresult.aspx' } r = requests.get(url=WyuLibrary.url_book_info, headers=_headers, params=_params, timeout=self._timeout) # _.d(r.content.decode(_.get_charset(r.content))) return r.content.decode(_.get_charset(r.content))
def _get_stu_info(self): r = requests.get('http://jwc.wyu.edu.cn/student/f1.asp', headers=self._headers, cookies=self._cookies) print r.content.decode(_.get_charset(r.content))
def __wyu_news(page): url = 'http://www.wyu.cn/news/default.asp' params = {'page': page} r = requests.get(url, params=params) encoding = _.get_charset(r.content) return r.content.decode(encoding)