def get_index_ec(self):
url = get_url("selective_course")
html = self._get_html(url)
not_error_page(html)
courses = parse_standard_table(html, "kcmcgrid", pure=True)
url_code = re.findall(r'xkkh=(.*?)&', html)
return url_code, courses
def get_course_detail(self, url_code):
special = "xkkh=%s&xh=%s"
_t = (url_code, self._info["xh"])
url = get_url("course_detail", special)
html = self._get_html(url, _t)
not_error_page(html, self.uid)
classroom_selection = re.findall(r'value="(.*?)".*?xkkh', html)
result = parse_standard_table(html, "xjs_table", pure=True)
return result, classroom_selection
def get_checkout_book(self, uid):
self.init_from_redis(uid, only_cookies=True)
res = safe_get(self.checkout_book_url,
headers=self.headers,
cookies=self.cookies)
html = res.content.decode("utf-8")
checkout_books = parse_standard_table(html,
class_name="table_line",
pure=True)
return checkout_books
def get_consume(self):
dates = self.cal_date()
data = {
"opertype": "query",
"startDate": dates[1],
"endDate": dates[0],
"input": "查询"
}
index = 1
consume = []
last_count = 0
while True:
if index == 1:
html = safe_post(self.consume_url,
data=data,
headers=self.headers,
cookies=self.cookies)
index += 1
else:
html = safe_get(self.consume_url +
"?opertype=page&page=%s" % index,
headers=self.headers,
cookies=self.cookies)
index += 1
html = html.content.decode("utf-8")
consume.extend(parse_standard_table(html, pure=True))
count = len(consume)
if count < 10 or (last_count != 10 and last_count == count):
break
else:
last_count = count
return consume
def search(self, keyword):
_url = self.opac_url + "search_adv_result.php?sType0=any&q0=%s&with_ebook=&page=%s"
url = _url % (keyword, 1)
html = safe_get(url, headers=self.headers).content.decode("utf-8")
page = etree.HTML(html)
books_num = int(
page.xpath(u"//div[@class='box_bgcolor']/font[last()]")[0].text)
current_page = 1
books = []
url_code = []
while True:
books.extend(
parse_standard_table(html, "result_content", pure=True))
url_code.extend(safe_re('marc_no=(.*)"', html))
current_page += 1
if current_page > math.ceil(books_num / 20):
break
url = _url % (keyword, current_page)
html = safe_get(url, headers=self.headers).content.decode("utf-8")
return books, url_code
def get_elective_course(self, category):
while True:
url = get_url("selective_course")
html, url = self._get_html(url, only_html=False)
if "三秒防刷" in html:
print("\n检测到三秒防刷，程序将睡眠三秒钟。")
time.sleep(3)
else:
break
viewstate = get_viewstate(html)
post_data = {
"__EVENTTARGET": "",
"__EVENTARGUMENT": "",
"__VIEWSTATE": viewstate,
"zymc": "",
"xx": "",
"Button2": "选修课程"
}
html = safe_post(url=url,
data=post_data,
headers=self._headers,
cookies=self._cookies).text
post_data["zymc"] = (category + "|院公选课5").encode("gb2312")
del post_data["Button2"]
num = 0
current_page = 1
courses = []
url_code = []
page_num = []
while True:
try:
post_data["__VIEWSTATE"] = get_viewstate(html)
html = safe_post(url=url,
data=post_data,
headers=self._headers,
cookies=self._cookies).text
_t = parse_standard_table(html, "kcmcgrid", pure=True)
courses.extend(_t)
_t = re.findall(r'xkkh=(.*?)&', html)
url_code.extend(_t)
if num == 0:
num = int(re.search(r'共(\d*)条记录！', html).group(1))
if (current_page % 10) == 1:
page_num = re.findall(r'kcmcgrid\$_ctl\d*\$_ctl\d*', html)
if (current_page // 10) == 1:
_n = 10 - (num // 10 - 9)
page_num = [
page_num[i] for i in range(len(page_num)) if i > _n
]
if len(page_num) == 0:
break
current_page += 1
post_data["__EVENTTARGET"] = page_num.pop(0).replace("$", ":")
except AttributeError:
print("\n检测到三秒防刷，程序将睡眠三秒钟。")
time.sleep(3)
return url_code, courses
def get_book_detail(self, marc_no):
url = self.opac_url + "item.php?marc_no=" + marc_no
html = safe_get(url, headers=self.headers).content.decode("utf-8")
remain_books = parse_standard_table(html, "item", pure=True)
return remain_books