2022-02-16 18:13:44 +03:00
|
|
|
|
|
|
|
def table_parser(soup, output):
|
|
|
|
#Date parser
|
|
|
|
date = (soup.find("main").findAll('span', style="color:black"))[1]
|
|
|
|
output["date"] = date.text.replace(u'\xa0', u'')
|
|
|
|
|
|
|
|
|
|
|
|
#Replaces parser
|
|
|
|
replaces = soup.findAll('tr')
|
|
|
|
for data in replaces:
|
|
|
|
|
|
|
|
text = (
|
|
|
|
data.find("td", valign="top")
|
|
|
|
.find("span", style="color:black")
|
|
|
|
.text.replace(u'\xa0', u'')
|
|
|
|
)
|
|
|
|
group = (
|
|
|
|
data.find("span", style="color:black")
|
|
|
|
.text.replace(" ", "").replace(u'\xa0', u''))
|
|
|
|
output["data"][group] = text
|
|
|
|
|
|
|
|
return output
|
|
|
|
|
|
|
|
|
2022-02-22 15:29:44 +03:00
|
|
|
def text_parser(soup, output):
|
|
|
|
main = soup.find("main")
|
|
|
|
|
|
|
|
text: str = ''
|
|
|
|
for j in main:
|
|
|
|
r_text = (
|
|
|
|
j.text
|
|
|
|
.replace(u"\xa0", u"")
|
|
|
|
.lstrip(" ").lower()
|
|
|
|
.replace("\r", "")
|
|
|
|
.replace("увага! навчання дистанційно!!!", "")
|
|
|
|
.replace("заміни до розкладу", "")
|
|
|
|
)
|
|
|
|
if r_text.replace("\n", "") == "": continue
|
|
|
|
text += r_text
|
2022-02-16 18:13:44 +03:00
|
|
|
|
2022-02-22 15:29:44 +03:00
|
|
|
data = text.split("\n")
|
2022-02-16 18:13:44 +03:00
|
|
|
|
2022-02-22 15:29:44 +03:00
|
|
|
output["date"] = data[1]
|
2022-02-16 18:13:44 +03:00
|
|
|
|
2022-02-22 15:29:44 +03:00
|
|
|
for p in data[2:]:
|
|
|
|
if p == "": continue
|
|
|
|
group, replaces = p.split(" ", maxsplit=1)
|
|
|
|
output["data"][group] = replaces
|
2022-02-16 18:13:44 +03:00
|
|
|
|
|
|
|
return output
|