def get_rotten_tomatoes_url(content: str) -> dict:
regex_pattern = r"https://www.rottentomatoes.com/.+/.+?(?=&)"
rotten_tomatoes_url = regex_search(content=content,
pattern=regex_pattern)
result = ({
"rotten_tomatoes_url": rotten_tomatoes_url
} if rotten_tomatoes_url else {})
return result
def get_seasons(content):
regex_pattern = r"(No.\sof\sseasons:\s\d{1,3})|(\d{1,2}\sseasons)"
reg_search = regex_search(content=content, pattern=regex_pattern)
if reg_search:
try:
_, seasons = reg_search.split(":")
except ValueError:
seasons, _ = reg_search.split(" ")
else:
seasons = None
result = {"seasons": int(seasons.strip())} if seasons else {}
return result
def get_person_awards(self) -> dict:
result = {"oscars": None, "oscar_nominations": None}
soup_selection = {
"soup": self.soup,
"method": self.find_all,
"tag": "span",
"class": "awards-blurb",
}
if css_selection := self.soup_selection(**soup_selection):
oscar_data = css_selection[0].get_text(strip=True)
search = regex_search(oscar_data, r"\d{1,2}")
if "Won" in oscar_data:
result.update({"oscars": search})
elif len(css_selection) > 1:
# If there is no oscar wins and nominations
result.update({"oscar_nominations": search})
wins, nominations = re.findall(
r"\d+", css_selection[-1].get_text(strip=True))
result.update({"wins": wins, "nominations": nominations})
def get_release_date(self) -> dict:
release_date = {}
soup_selection = {
"soup": self.soup,
"method": self.find,
"tag": "li",
"dataset-testid": "title-details-releasedate",
}
if css_selection := self.soup_selection(**soup_selection):
# ['Release date', 'December 21, 2001 (Turkey)']
selection_list = css_selection.get_text("~").split("~")
regex_pattern = r"(^.*?\d{4})"
search = regex_search(selection_list[1], regex_pattern)
try:
date_time = get_date_time(search, "%B %d. %Y")
except ValueError:
try:
date_time = get_date_time(search, "%B %d, %Y")
except ValueError:
date_time = get_date_time(search, "%B %d. %Y")
release_date = {"release_date": date_time}
def get_tv_com_rate(content: str) -> dict:
regex_pattern = r"(\d.\d|\d)/10\s.\sTV.com"
tv_com_rate = regex_search(content=content, pattern=regex_pattern)
result = {"tv_com_rate": tv_com_rate} if tv_com_rate else {}
return result
def get_imdb_url(content: str) -> dict:
regex_pattern = r"https://www.imdb.com/title/[^;]*/"
imdb_url = regex_search(content=content, pattern=regex_pattern)
result = {"imdb_url": imdb_url} if imdb_url else {}
return result