replace-bot/parser/utils.py

69 lines
2.0 KiB
Python
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

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
def one_parser(soup, output):
raw_data = soup.find("main").findAll("p")
date = (
raw_data[3].text.lower()
.replace(u"\xa0", u"").replace("на", "").replace("\r", "")
.replace("ЗАМІНИ ДО РОЗКЛАДУ".lower(), "").split("\n")
)
output["date"] = date[0].lstrip(" ")
for p in raw_data[4].text.replace(u"\xa0", u"").split("\n"):
if p == "": continue
data_rep = (p.lstrip(" ").split(" ", 1))
group = data_rep[0]
text = data_rep[1].replace("\r", "").lstrip(" ")
output["data"][group] = text
return output
def parser_two(soup, output):
raw_data = soup.find("main").findAll("p")[2]
data = raw_data.text.split("\n")
output["date"] = data[1].replace("\r", "")
for p in data[3:]:
r_data = p.split(maxsplit=1)
try:
group = r_data[0].replace(u"\xa0", u"").replace("\r", "")
text = r_data[1].replace(u"\xa0", u"").replace("\r", "")
except IndexError: break
output["data"][group] = text
return output
def parser3(soup, output):
raw_data = soup.find("main").findAll("p")
output["date"] = (
raw_data[2].text
.replace("\r", "")
.replace("ЗАМІНИ НА", "").lstrip(" ").rstrip(" ").lower()
)
for p in raw_data[5:]:
r_data = p.text.split("-", maxsplit=1)
group = r_data[0]
text = r_data[1]
output["data"][group] = text
return output