def __serialize_listing(self, listing_element: PageElement):
title_element = listing_element.find_next(class_="listing_header")
title = title_element.text
price_text = listing_element.find_next(class_="price").text
price = int(re.sub("[^0-9]", "", price_text))
body = listing_element.find_next(class_="body").text
listing = BarnstormersClassifiedListing()
listing.title = title
listing.price = price
listing.description = body
listing.url = self.base_url + title_element["href"]
return listing
def __parse_result_item(self, result_item: PageElement):
result_title = result_item.find_next(id='title')
price_text = re.sub("[^0-9]", "",
result_item.find_next(class_='txt-price').text)
price = 0
description = result_item.find_next(class_='description').text.strip()
url = self.base_url + result_title['href']
if len(price_text) != 0:
price = int(price_text)
return TradeAPlaneListing(title=result_title.text.strip(),
price=price,
description=description,
url=url)
def _format_vacancy(item: PageElement):
data = {
"site_id":
int(
item.find_next(
"a", {"class": "no-decoration"})['href'].split("/")[-2]),
"title":
item.find_next("a").get_text(),
"company":
item.find_next("div", {
"class": "add-top-xs"
}).find_next("b").get_text(),
"desc":
" ".join(
unicodedata.normalize("NFKD",
item.find_next("p").get_text()).split()),
"salary":
unicodedata.normalize("NFKD", a)
if "грн" in (a := item.find_next("b").get_text()) else None,
"city":
"|".join([
i.replace('\xa0', ' ')
for i in item.find_next("div", {
"class": "add-top-xs"
}).get_text().split("·")[1:]
]),
"link":
"https://work.ua" +
item.find_next("a", {"class": "no-decoration"})['href']
}
return data
def _format_vacancy(item: PageElement):
data = {
"site_id":
int(item["data-vacancy-id"]),
"title":
item.find_next("a", {
"class": "ga_listing"
}).get_text().replace("\n", ""),
"company":
item.find_next("a", {
"class": "company-profile-name"
}).get_text(),
"desc":
item.find_next("div", {
"class": "card-description"
}).get_text(),
"salary":
a if (a := item.find_next("span", {
"class": "salary"
}).get_text()) else None,
"city":
item.find_next("span", {
"class": "location"
}).get_text(),
"link":
"https://robota.ua" +
item.find_next("a", {"class": "ga_listing"})['href']
}
return data
def _format_vacancy(item: PageElement):
data = {
"site_id":
int(item["_id"]),
"title":
item.find_next("a", {
"class": "vt"
}).get_text(),
"company":
item.find_next("a", {
"class": "company"
}).get_text().replace('\xa0', ''),
"desc":
" ".join(
unicodedata.normalize(
"NFKD",
item.find_next("div", {
"class": "sh-info"
}).get_text()).split()),
"salary":
unicodedata.normalize("NFKD", a.get_text()) if
(a := item.find_next("span", {"class": "salary"})) else None,
"city":
item.find_next("span", {
"class": "cities"
}).get_text(),
"link":
item.find_next("a", {"class": "vt"})['href']
}
return data
