def main():
print("! Getting a list of TV shows from eztv...")
showlist_page = lxml.html.fromstring(requests.get(EZTV_URL).content)
shows = [l.text for l in showlist_page.xpath('//a[@class="thread_link"]')]
print("")
imdb = Imdb()
episode_records = []
for show_name in shows[:10]:
print("* Processing `{}`...".format(show_name))
episodes = None
for show in imdb.search_for_title(show_name):
try:
episodes = imdb.get_episodes(show['imdb_id'])
break
except (RuntimeError, TypeError):
# RuntimeError: This is thrown when a show is not recognized a series
# TypeError: Bug where seasons is None.
continue
if episodes is None:
print(" ! Couldn't find an IMDB entry for `{}`. Ignoring.".format(
show_name))
continue
episode_records += [e.__dict__ for e in episodes]
df = pd.DataFrame(episode_records)
df.to_csv(DATA_PATH, index=False)
class imdb_api:
def __init__(self, anonymize=False):
self.imdb = Imdb(anonymize=anonymize)
def search(self, title, imdb_id=""):
if not imdb_id:
print("Searching")
results = self.imdb.search_for_title(title)
chosen = self.search_select(results)
title_id = results[chosen]["imdb_id"]
else:
title_id = imdb_id
print("Looking up series")
title = self.imdb.get_title_by_id(title_id)
if title.type == "tv_series":
print("Detected TV series, downloading episode list")
episodes = self.imdb.get_episodes(title_id)
print(episodes)
return [title, episodes]
else:
return [title]
def search_select(self, results):
def get_input(allow_0=True):
print("Which show do you want? type 0 to see more")
out = 0
while out == 0:
inp = input("> ")
if inp == "0" and allow_0:
return out
else:
try:
out = int(inp)
except ValueError:
print("Not a number")
return out
if len(results) > 1:
chosen = 0
for index, show in enumerate(results):
print("[{0}] ({3})\t{1}\t{2}".format(str(index + 1),
show["title"],
show["year"],
show["imdb_id"]))
if ((index + 1) % 10) == 0:
chosen = get_input()
if chosen != 0:
break
if chosen == 0:
print("No more")
chosen = get_input(allow_0=False)
return chosen - 1
#imdb = imdb_api()
#x = imdb.search("Person of Interest")
#print(x)
def test_get_episodes(self):
assert self.imdb.get_title_by_id('tt0303461') is not None
imdb = Imdb()
episodes = imdb.get_episodes('tt0303461')
assert episodes is not None
assert len(episodes) == 14
episode_1 = episodes[0]
assert episode_1.imdb_id == "tt0579539"
assert episode_1.type == "tv_episode"
assert episode_1.title == u'The Train Job'
assert episode_1.series_name == 'Firefly'
assert episode_1.release_date == "2002-09-20"
assert episode_1.year == 2002
def test_get_episodes(self):
assert self.imdb.get_title_by_id('tt0303461') is not None
imdb = Imdb()
episodes = imdb.get_episodes('tt0303461')
assert episodes is not None
assert len(episodes) == 14
episode_1 = episodes[0]
assert episode_1.imdb_id == "tt0579539"
assert episode_1.type == "tv_episode"
assert episode_1.title == u'The Train Job'
assert episode_1.series_name == 'Firefly'
assert episode_1.release_date == "2002-09-20"
assert episode_1.year == 2002
def seasonBuilder(title):
# gets the information of the show in general
# Also gets the seasons and episdoes in a dict to use in the other file
# iniatilize imdb object
imdb = Imdb()
imdb = Imdb(anonymize=True)
title_json = imdb.search_for_title(title)
if title_json == []:
print('No Results Found')
else:
# get imdb id to get more information
title_id = title_json[0]['imdb_id']
result = imdb.get_title_by_id(title_id)
show_title = result.title
year = result.year
image_url = result.cover_url
description = result.plot_outline
temp = imdb.get_episodes(title_id)
# build season dict to send back to main file
seasons = {}
episodes = {}
season_counter = 1
for e in temp:
# new dict entry for the next season, the number season of the show is the entry key
if e.season > season_counter:
# the current season is done, time to start building the next episiode dict
seasons[season_counter] = episodes
episodes = {}
season_counter += 1
episodes[e.episode] = [e.title, e.release_date, e.imdb_id]
return show_title, year, image_url, description, seasons
def receive_episodes(ep_no):
try:
global to_download
imdb = Imdb()
z = imdb.get_episodes(ep_no)
for item in z:
if item.release_date == yesterday:
if item.season < 10:
season = "0" + str(item.season)
else:
season = str(item.season)
if item.episode < 10:
ep = "0" + str(item.episode)
else:
ep = str(item.episode)
new_item = item.series_name + ' s' + season + 'e' + ep + '\n'
to_download = to_download + new_item
except Exception as err5:
err_msg5 = (str(err5), 'Error Origin: Receive Episodes')
print(err_msg5)
del err_msg5
class Watcher:
def __init__(self):
self.imdb = Imdb(anonymize=True)
self.tracked_shows = self.get_shows()
self.static_dir = os.path.join(os.path.dirname(__file__),
'../static/images')
def get_shows(self):
"""
gets all current popular shows from imdb
"""
shows = self.imdb.popular_shows()
tracked_shows = []
for show in shows:
tracked_shows_d = {}
tracked_shows_d['id'] = show['tconst']
tracked_shows_d['title'] = show['title']
tracked_shows_d['poster'] = show['image']['url']
tracked_shows.append(tracked_shows_d)
return tracked_shows
def get_show_id(self, show_title):
"""
Gets show title id
args:
show_title: name of show to be queried
returns:
show_id: id of show
"""
for show in self.tracked_shows:
if show_title == show['title']:
return show['id']
def get_episodes(self, show_id):
"""
Gets all episodes of a given show
args:
show_id: tconst id from imdb
returns:
ist of episodes
"""
return self.imdb.get_episodes(show_id)
def get_all_episodes(self):
"""
Gets all episodes
args:
None
returns:
list of episodes for all shows"""
programs = {}
for show in self.tracked_shows:
programs[show['title']] = self.get_episodes(show['id'])
return programs
def get_poster(self, show_title):
"""
gets the img url for the poster of a show
args:
show_title: title of show
returns:
dictionary with {show_title: poster_url}
"""
#print(self.tracked_shows[show_id]['poster'])
for show in self.tracked_shows:
if show['title'] == show_title:
return {show_title: show['poster']}
def save_posters(self, urls, title):
title = self.sanitize_title(title)
dest = '{}/{}.jpg'.format(self.static_dir, title)
urllib.request.urlretrieve(url, dest)
def sanitize_title(self, title):
forbidden = ('<', '>', ':', '"', '/', '\\', '|', '?', '*')
for char in forbidden:
title = title.replace(char, '')
return title
def get_show_titles(self):
"""
Gets show titles
args:
None
returns:
list of show titles
"""
return [show['title'] for show in self.tracked_shows]
# https://github.com/richardasaurus/imdb-pie
from imdbpie import Imdb
imdb = Imdb()
imdb = Imdb(anonymize=True)
print(imdb.search_for_title("The Dark Knight"))
print()
print(imdb.search_for_person("Christian Bale"))
print()
print(imdb.get_episodes('tt0096697'))
top250 = imdb.top_250()
for i in range(0, len(top250)):
print(top250[i])
print()
title = imdb.get_title_by_id("tt1210166")
for person in title.credits:
# check if they are a writer
if person.token == 'writers':
print(person.name + ' is a writer')
else:
print(person.name + ' is not a writer')
def test_get_episodes_raises_when_exclude_episodes_enabled(self):
imdb = Imdb(locale='en_US', cache=False, exclude_episodes=True)
with pytest.raises(ValueError):
imdb.get_episodes('tt0303461')
def test_get_episodes_raises_when_exclude_episodes_enabled(self):
imdb = Imdb(locale="en_US", cache=False, exclude_episodes=True)
with pytest.raises(ValueError):
imdb.get_episodes("tt0303461")
async def imdb(query, api: Imdb, localize):
"""
Send an api request to imdb using the search query
:param query: the search query
:param api: the imdb api object
:param localize: the localization strings
:return: the result
"""
# FIXME: Use Aiohttp instead of this api wrapper
try:
names = lambda x: ', '.join((p.name for p in x)) if x else 'N/A'
null_check = lambda x: x if x and not isinstance(x, int) else 'N/A'
id_ = api.search_for_title(query)[0]['imdb_id']
res = api.get_title_by_id(id_)
eps = api.get_episodes(id_) if res.type == 'tv_series' else None
ep_count = len(eps) if eps is not None else None
season_count = eps[-1].season if eps is not None else None
title = null_check(res.title)
release = null_check(res.release_date)
runtime = res.runtime
if runtime is not None:
hours, seconds = divmod(runtime, 3600)
minutes = seconds / 60
runtime_str = '{} {} {} {}'.format(round(hours), localize['hours'],
round(minutes),
localize['minutes'])
else:
runtime_str = 'N/A'
rated = null_check(res.certification)
genre = ', '.join(res.genres) if res.genres else 'N/A'
director = names(res.directors_summary)
writer = names(res.writers_summary)
cast = names(res.cast_summary)
plot = null_check(res.plot_outline)
poster = res.poster_url
score = f'{res.rating}/10' if res.rating is not None else 'N/A'
embed = Embed(colour=0xE5BC26)
embed.set_author(name=title)
if poster:
embed.set_image(url=poster)
if season_count is not None:
embed.add_field(name=localize['seasons'], value=season_count)
if ep_count is not None:
embed.add_field(name=localize['episodes'], value=str(ep_count))
embed.add_field(name=localize['release_date'], value=release)
embed.add_field(name=localize['rated'], value=rated)
embed.add_field(name=localize['runtime'], value=runtime_str)
embed.add_field(name=localize['genre'], value=genre)
embed.add_field(name=localize['director'], value=director)
embed.add_field(name=localize['writer'], value=writer)
embed.add_field(name=localize['cast'], value=cast)
embed.add_field(name=localize['score'], value=score)
embed.add_field(name=localize['plot_outline'],
value=plot,
inline=False)
return embed
except (JSONDecodeError, IndexError):
return localize['title_not_found']
