def _get_latest_season(self):
webpage = get_parsed_webpage(f"{self.url}/episodes?season=0")
self.latest_season = self._get_season_data(webpage)
# Check to see if the latest season(s) are empty empty - Edge case
while all([
episode["rating"] == ""
for episode in self.latest_season["episodes"]
]):
latest = self.latest_season["number"] - 1
webpage = get_parsed_webpage(
f"{self.url}/episodes?season={latest}")
self.latest_season = self._get_season_data(webpage)
def search_imdb(query):
encoded = urllib.parse.quote(query)
url = f"https://www.imdb.com/find?q={encoded}&s=tt&ttype=tv"
webpage = get_parsed_webpage(url)
lst = webpage.find("table", class_="findList")
if lst is None:
return []
return list(
filter(
lambda show: show is not None,
(get_data_from_row(child) for child in lst.children),
)
)
def get_show_ids():
webpage = get_parsed_webpage("https://www.imdb.com/chart/toptv/")
list_div = webpage.find("div", class_="lister")
lst = list_div.select_one("table.chart tbody ")
for num, row in enumerate(lst.children):
try:
title_cell = row.find("td", class_="titleColumn")
link = title_cell.find("a")
title = link.text.strip()
id_ = get_id_from_link(link["href"])
yield title, id_
except:
continue
def get_all_seasons(self):
"""
Returns a generator of dictionaries (seasons),
each contains an "episodes" key with a list of episodes for that season.
"""
seasons = range(1, self.latest_season["number"])
if self.log:
seasons = tqdm(seasons, desc="Seasons")
for season in seasons:
episode_list_url = f"{self.url}/episodes?season={season}"
webpage = get_parsed_webpage(episode_list_url)
self.episode_data.append(
self._get_season_data(season_page=webpage))
self.episode_data.append(self.latest_season)
def _get_show_data(self):
"""
Returns a dictionary of show level data
"""
webpage = get_parsed_webpage(self.url)
details = webpage.find(class_="title_bar_wrapper")
title = details.select(".title_wrapper h1")[0].text.strip()
rating = details.select(
".ratings_wrapper .ratingValue span")[0].text.strip()
num_ratings = details.select(
".ratings_wrapper a span.small")[0].text.strip()
num_episodes = (webpage.find(class_="navigation_panel").find(
class_="bp_sub_heading").text.replace("episodes", "").strip())
additional_details_tag = details.find(class_="subtext")
additional_details = IMDBScraper._get_additional_details(
additional_details_tag)
plot_details = webpage.find(class_="plot_summary")
summary = plot_details.find(class_="summary_text").text.strip()
cast = plot_details.find_all(class_="credit_summary_item")
if len(cast) == 1:
stars = cast[0]
creators = []
else:
creators, stars = cast
creators = list(map(lambda x: x.text.strip(), creators("a")))
stars = list(map(lambda x: x.text.strip(), stars("a")))
poster_div = webpage.find("div", class_="poster")
poster = poster_div.find("img")["src"]
data = dict(
title=title,
rating=rating,
num_ratings=num_ratings,
num_episodes=num_episodes,
plot_summary=summary,
creators=creators,
stars=stars,
poster_url=poster,
)
data.update(additional_details)
self.show_data = data