def get_episodes(self, show_id, season):
r = self.session.get(f"{BASE_URL}/show/{show_id}/{season}")
r.raise_for_status()
sopa = bso(r.content, "lxml")
tables = sopa.find_all("tr")
seasons = [i.text for i in tables[1].find_all("a")]
if not any(season == season_ for season_ in seasons):
return
season_subs = []
episodes = []
for tr in range(len(tables)):
data = tables[tr].find_all("td")
title = self.title_available(data)
if title:
episodes.append(title)
source_var = self.source_separator(data)
if not source_var:
continue
season_subs += list(
self.scrape_episode_info(source_var, tables, tr))
return list(self.get_episode_dicts(episodes, season_subs, season))
def download_lastfm_pl(self, playlist_url):
# Apparently, last fm API doesn't have a playlist endpoint. If you
# find out that it has, please fix this!
try:
r = requests.get(playlist_url, timeout=10)
except requests.exceptions.RequestException as e:
logger.error(f"{RED}Playlist download failed: {e}")
return
soup = bso(r.content, "html.parser")
artists = [artist.text for artist in soup.select(ARTISTS_SELECTOR)]
titles = [title.text for title in soup.select(TITLE_SELECTOR)]
track_list = []
if len(artists) == len(titles) and artists:
track_list = [
artist + " " + title for artist, title in zip(artists, titles)
]
if not track_list:
logger.info(f"{OFF}Nothing found")
return
pl_title = sanitize_filename(soup.select_one("h1").text)
pl_directory = os.path.join(self.directory, pl_title)
logger.info(f"{YELLOW}Downloading playlist: {pl_title} "
f"({len(track_list)} tracks)")
for i in track_list:
track_id = get_url_info(
self.search_by_type(i, "track", 1, lucky=True)[0])[1]
if track_id:
self.download_from_id(track_id, False, pl_directory)
if not self.no_m3u_for_playlists:
make_m3u(pl_directory)
def random_posts(html):
soup = bso(html, "lxml")
posts = list(soup.findAll(attrs={"role": "main"})[0].children)
result = []
for i in range(3):
result.append(str(posts[random.randint(0, len(posts))]))
return result
def getFakeAccData(self, response):
beautifulContent = bso(response.content, "html.parser")
mailAdress = self.getMailAdress(beautifulContent)
cookies = self.getCookies(response)
return mailAdress, cookies
def parse_pdf(path):
"""
Parses a pdf to string. Reads the pdf from the given path
"""
raw = parser.from_file(path, xmlContent=True)
soup = bso(raw['content'], 'lxml')
pages = soup.find_all('div', attrs={'class': 'page'})
print(pages)
return pages
def index_titles(self):
r = self.session.get(f"{BASE_URL}/series.php?/")
r.raise_for_status()
soup = bso(r.content, "html.parser")
for a in soup.find_all("a"):
href_url = a.get("href")
if "show" in href_url:
yield {"title": a.text, "url": href_url}
def index_titles(self):
r = self.session.get(BASE)
r.raise_for_status()
soup = bso(r.content, "html.parser")
titles = []
for a in soup.find_all("a"):
href_url = a.get("href")
if "show" in href_url:
titles.append({"title": a.text, "url": href_url})
return titles
def get_tickers_list_SP500():
import urllib
from urllib import request
from bs4 import BeautifulSoup as bso
url = "https://en.wikipedia.org/wiki/List_of_S%26P_500_companies"
# Get page
if not os.path.exists("wiki_tickers_page.txt"):
get_url = request.urlopen(url).read()
with open("wiki_tickers_page.txt", "w") as file:
file.write(str(get_url))
else:
with open("wiki_tickers_page.txt", "r") as file:
get_url = file.read()
# Get Ticker
bsdoc = bso(get_url, "html.parser")
table = bsdoc.find("table", {"id": "constituents"})
# print(table)
table = table.find("tbody")
if not os.path.exists("tickers.txt"):
# print(get_url)
a_ = table.findAll("a", {"class": "external text"})
tickers = []
for a in a_:
if a.getText() != "reports":
tickers.append(str(a.getText()))
with open("tickers.txt", "w") as file:
file.write(json.dumps(tickers))
print("tickers file created")
else:
with open("tickers.txt", "r") as file:
tickers = json.loads(file.read())
if not os.path.exists("tickers_names.txt"):
names = []
trs = table.findAll("tr")
i = 0
for tr in trs:
#print(tr)
tds = bso.findAll(tr, "td")
#ais = bso.findAll(tds, "a")
for i, td in enumerate(tds):
#print(i, td)
if i == 1:
name = bso.find(td, "a").getText()
names.append(name)
with open("tickers_names.txt", "w") as file:
file.write(json.dumps(names))
else:
with open("tickers_names.txt", "r") as file:
names = json.loads(file.read())
return tickers, names
def getInboxLinks(self, response):
beautifulContent = bso(response.content, "html.parser")
inboxElements = beautifulContent.find("table")
trimmedLinks = []
for mails in inboxElements.contents:
link = mails.attrs.get('onclick')
if (link):
extractedLink = re.findall("readmail.html.*'", link)
trimmedLinks.append(extractedLink[0].strip("'"))
return trimmedLinks
def getTwitterCode(self, response):
beautifulContent = bso(response.content, "html.parser")
codes = beautifulContent.findAll("td",
attrs={
"class": "h1 black",
"dir": "ltr"
})
for code in codes:
code = code.getText()
if code.isnumeric():
return code
else:
return -1
def get_html_soup_object(url):
try:
fp = urllib.request.urlopen(url)
mybytes = fp.read()
fp.close()
except HTTPError as e:
mybytes = e.read()
except URLError:
print("Błąd sieci! Upewnij się czy działa połączenie z internetem.")
sys.exit(2)
html = mybytes.decode("utf8")
return bso(html, "html.parser")
def get_arg_links(moviePag):
moviePag = requests.get("%s?id=%s" % (api_movie, arg_id))
movieSop = bso(moviePag.content, "html.parser")
movieJson = json.loads(movieSop.text)
movieTitle = movieJson["title"]
try:
for rele in movieJson["releases"]:
if rele["subtitles"]:
for uri in rele["subtitles"]:
self.appendSubs(
movieTitle,
uri["uri"].rsplit("/", 1)[-1],
uri["uri"],
"argenteam.net",
)
except KeyError:
pass
def get_subdivx(self):
subdivx = "{}{}{}".format(subdivx_base, self.query, subdivx_query)
page = requests.get(subdivx)
soup = bso(page.content, "html.parser")
title = soup.find_all(id="menu_titulo_buscador")
desc = soup.find_all(id="buscador_detalle_sub")
url = soup.find_all("a", class_="titulo_menu_izq")
for t, d, u in zip(title, desc, url):
self.appendSubs(
t.text.replace("Subtitulos de ", ""),
d.text,
u.get("href"),
"subdivx.com",
)
if not title:
print("Sin resultados en Subdivx")
def get_tickers_list_PA():
import urllib
from urllib import request
from bs4 import BeautifulSoup as bso
from string import ascii_uppercase
alphabet = [letter for letter in ascii_uppercase]
url = "https://www.borsaitaliana.it/borsa/azioni/listino-a-z.html?initial="
for letter in alphabet:
ticker_page = request.urlopen(url + letter).read()
table = bso(ticker_page,
"html.parser").find("table",
{"class": "m-table -firstlevel"})
table_body = table.findAll("tr")
for row in table_body:
print(row)
print(table)
def scrape_download_url(self, episode_dict):
logger.debug("Scrapping download URL")
r = self.session.get(episode_dict["download_url"])
r.raise_for_status()
discriminator = f".{episode_dict['season']}.{episode_dict['episode']}."
soup = bso(r.content, "lxml")
for url, selected in zip(soup.select(CSS1), soup.select(CSS2)):
meta = ".".join(
selected.get("href").split(discriminator)[-1].split(".")[:-1])
if meta in episode_dict["download_url"]:
id_url = url.find_all("a")[0].get("href")
sub_id = parse.parse_qs(parse.urlparse(id_url).query)["id"][0]
lang_id = parse.parse_qs(
parse.urlparse(id_url).query)["lang"][0]
version_ = parse.parse_qs(
parse.urlparse(id_url).query)["fversion"][0]
return f"{BASE_URL}/updated/{lang_id}/{sub_id}/{version_}"
def parse(self, response):
'''Need regex to grab the time from the date and price attributes'''
# print(response.css('ul.search-main-content__events-list').extract())
ul_selector = response.css(
"ul.search-main-content__events-list").extract_first()
soup = bso(ul_selector, "lxml")
unordered_list = soup.find("ul")
print(unordered_list)
# print(first_child.findChildren())
list_of_tags = unordered_list.children
# print(list_of_tags)
all_events = list()
# print(list_of_tags)
for item in list_of_tags:
event = Event()
div_container = response.css(
'div.eds-media-card-content__content__principal')
# print(div_container)
event['title'] = div_container.css(
"a.eds-media-card-content__action-link h3.eds-media-card-content__title.eds-text-color--grey-800.eds-text-bl div.card-text--truncated__three::text"
).extract_first()
event['date'] = div_container.css(
'div.eds-media-card-content__sub-content div.eds-text-bs--fixed.eds-text-color--grey-600.eds-l-mar-top-1::text'
).extract_first()
event['location'] = div_container.css(
'div.eds-media-card-content__sub-content div.eds-media-card-content__sub-content-cropped div.eds-text-bs--fixed.eds-text-color--grey-600.eds-l-mar-top-1 div.card-text--truncated__one::text'
).extract_first()
event['price'] = div_container.css(
'div.eds-media-card-content__sub-content div.eds-media-card-content__sub-content-cropped div.eds-text-bs--fixed.eds-text-color--grey-600.eds-l-mar-top-1::text'
).extract_first()
return event
def download_lastfm_pl(self, playlist_url):
# Apparently, last fm API doesn't have a playlist endpoint. If you
# find out that it has, please fix this!
r = requests.get(playlist_url)
soup = bso(r.content, "html.parser")
artists = [artist.text for artist in soup.select(ARTISTS_SELECTOR)]
titles = [title.text for title in soup.select(TITLE_SELECTOR)]
if len(artists) == len(titles) and artists:
track_list = [
artist + " " + title for artist, title in zip(artists, titles)
]
if not track_list:
print("Nothing found")
return
pl_title = sanitize_filename(soup.select_one("h1").text)
print("Downloading playlist: " + pl_title)
self.directory = os.path.join(self.directory, pl_title)
for i in track_list:
track_url = self.search_by_type(i, "track", 1, lucky=True)[0]
if track_url:
self.handle_url(track_url)
def get_argenteam(self):
argenteam_search = "%s?q=%s" % (api_search, self.query)
page = requests.get(argenteam_search)
soup = bso(page.content, "html.parser")
arg_json = json.loads(soup.text)
def get_arg_links(moviePag):
moviePag = requests.get("%s?id=%s" % (api_movie, arg_id))
movieSop = bso(moviePag.content, "html.parser")
movieJson = json.loads(movieSop.text)
movieTitle = movieJson["title"]
try:
for rele in movieJson["releases"]:
if rele["subtitles"]:
for uri in rele["subtitles"]:
self.appendSubs(
movieTitle,
uri["uri"].rsplit("/", 1)[-1],
uri["uri"],
"argenteam.net",
)
except KeyError:
pass
for tipo in arg_json["results"]:
mov_o_tv = tipo["type"]
arg_id = tipo["id"]
try:
if mov_o_tv == "movie":
moviePag = requests.get("{}?id={}".format(api_movie, arg_id))
get_arg_links(moviePag)
else:
moviePag = requests.get("{}?id={}".format(api_episode, arg_id))
get_arg_links(moviePag)
except AttributeError:
print("Sin resultados en Argenteam")
def get_content_entries(counter):
html = get_html()
if html:
soup = bso(html, "html.parser")
bodies = soup.find_all("body")
titles = soup.find_all("title")
letters_body_list = []
for idx, (body, title) in enumerate(zip(bodies, titles)):
letter_dict = {
"letter_number": idx, # ex-letter_order
"letter_title": title.text,
"body": body
}
letters_body_list.append(letter_dict)
wasted_letters_numbers = [2, 4, 8, 16]
without_li_letters_numbers = [6, 7, 10, 11]
strong_theme_letters = [5, 9, 12, 13, 14, 15, 17]
for idx, letter in enumerate(letters_body_list):
# for i in without_li_letters_numbers:
# print(letters_body_list[i]["letter_title"])
# exit(0)
# continue
# letter = letters_body_list[10]
# letter["letter_number"] = 12
# letter["body"] = letters_body_list[12]["body"]
# letter["letter_title"] = letters_body_list[12]["letter_title"]
if letter["letter_number"] in wasted_letters_numbers:
continue
else:
section_name = letter["letter_title"]
modified_date = get_modified_date(section_name)
get_all_a_in_text(letter["body"], letter["letter_title"],
modified_date)
# # text = get_text(letter["body"], 31, -16)
description = section_name
lesson_name = pretifier(section_name)
url = "text_" + str(counter)
counter += 1
write_to_db(lesson_name,
description,
section_name,
url,
modified_date=modified_date,
url_description=str(letter["body"]))
if letter["letter_number"] == 5: # виртуальное окружение
ol = letter["body"].find('ol')
for li in ol.find_all('li'):
list_a = li.find_all('a')
for a in list_a:
description = li.text
lesson_name = pretifier(li.text)
section_name = letter["letter_title"]
url_description = a.text
url, type = get_url_and_url_type(a)
slug = get_slug_url(
lesson_name, section_name
) # возможно стоит передавать description вместо lesson_name. Проверить!
write_to_db(lesson_name,
description,
section_name,
url,
modified_date=modified_date,
url_description=url_description,
type=type,
slug=slug)
if letter[
"letter_number"] in strong_theme_letters: # недели 4,5,6,7,8 (тесты), 9
strongs = letter["body"].find_all("strong")
for strong in strongs:
next_ = strong.find_next()
if next_.li:
li_list = next_.find_all("li")
for li in li_list:
section_name = strong.text
lesson_name = pretifier(li.text)
description = li.text
url_description = letter["letter_title"]
url, type = get_url_and_url_type(li.a)
slug = get_slug_url(
lesson_name, section_name
) # возможно стоит передавать description вместо lesson_name. Проверить!
write_to_db(lesson_name,
description,
section_name,
url,
modified_date=modified_date,
url_description=url_description,
type=type,
slug=slug)
elif "проекты" in strong.text.lower():
next_next_ = next_.find_next().find_next()
section_name = letter["letter_title"]
url_description = next_next_.text
lesson_name = pretifier(strong.text)
description = strong.text
url, type = get_url_and_url_type(next_next_)
slug = get_slug_url(
lesson_name, section_name
) # возможно стоит передавать description вместо lesson_name. Проверить!
write_to_db(lesson_name,
description,
section_name,
url,
modified_date=modified_date,
url_description=url_description,
type=type,
slug=slug)
next_next_next_ = next_next_.find_next()
section_name = letter["letter_title"]
url_description = next_next_next_.text
description = strong.text
lesson_name = pretifier(strong.text)
url, type = get_url_and_url_type(next_next_next_)
slug = get_slug_url(
lesson_name, section_name
) # возможно стоит передавать description вместо lesson_name. Проверить!
write_to_db(lesson_name,
description,
section_name,
url,
modified_date=modified_date,
url_description=url_description,
type=type,
slug=slug)
elif "трек" in strong.text.lower(
) or "дополнительно" in strong.text.lower():
# continue
if "5-й недели" in letter["letter_title"].lower():
next_next_ = next_.find_next().find_next(
).find_next()
elif "трек" in strong.text.lower(
) or "9 недели" in letter["letter_title"].lower():
next_next_ = next_.find_next().find_next()
elif "дополнительно" in strong.text.lower():
next_next_ = next_.find_next()
li_list = next_next_.find_all("li")
for li in li_list:
section_name = strong.text.replace('"', '')
lesson_name = pretifier(li.text)
description = li.text
url_description = letter["letter_title"]
url, type = get_url_and_url_type(li.a)
slug = get_slug_url(
lesson_name, section_name
) # возможно стоит передавать description вместо lesson_name. Проверить!
write_to_db(lesson_name,
description,
section_name,
url,
modified_date=modified_date,
url_description=url_description,
type=type,
slug=slug)
elif letter[
"letter_number"] in without_li_letters_numbers: # Trello, проекты, доп задания
lesson_name = pretifier(section_name)
description = section_name
regex = re.compile(
r".*gmail.com.*|.*subscri*.|why did I get this")
tables = letter["body"].find_all("table")
for td in tables:
list_a = td.find_all('a')
for a in list_a:
match = regex.search(a.text)
if not match:
url, type = get_url_and_url_type(a)
url_description = a.text
slug = get_slug_url(
lesson_name, section_name
) # возможно стоит передавать description вместо lesson_name. Проверить!
write_to_db(lesson_name,
description,
section_name,
url,
modified_date=modified_date,
type=type,
url_description=url_description,
slug=slug)
else:
# недели: 0(приветственное), 1, 2
# text = get_text(letter["body"], 31, -16)
# theme_name = section_name
# url = "text_" + str(counter)
# counter += 1
# slug = get_slug_url(theme_name, section_name)
# write_to_db(theme_name, section_name, url, modified_date=modified_date, description=str(letter["body"]), slug=slug)
# continue
li_els = letter["body"].find_all('li')
for li in li_els:
if li.a:
a_els = li.find_all('a')
for a in a_els:
lesson_name = pretifier(li.text)
description = li.text
url_description = a.text
url, type = get_url_and_url_type(a)
slug = get_slug_url(
lesson_name, section_name
) # возможно стоит передавать description вместо lesson_name. Проверить!
write_to_db(lesson_name,
description,
section_name,
url,
modified_date=modified_date,
url_description=url_description,
type=type,
slug=slug)
else:
print('\t[Error] No datafile found')
def __init__(self, data):
self.engine = bso(data, "lxml")
def updateData(self, data):
self.engine = bso(data, "lxml")
def convert_one(input_file):
soup = bso(open(input_file), 'xml')
newsoup = bso('<annotation></annotation>', 'xml')
ann = newsoup.annotation
filename = soup.annotation.filename.string
folder = soup.annotation.folder.string
folder_tag = newsoup.new_tag('folder')
filename_tag = newsoup.new_tag('filename')
folder_tag.string = "VOC10"
filename_tag.string = filename
ann.append(folder_tag)
ann.append(filename_tag)
source_tag = newsoup.new_tag('source')
db_tag = newsoup.new_tag('database')
db_tag.string = 'The VOC2007 Database'
src_ann_tag = newsoup.new_tag('annotation')
src_ann_tag.string = 'PASCAL VOC2007'
img_tag = newsoup.new_tag('image')
img_tag.string = 'flickr'
source_tag.append(db_tag)
source_tag.append(src_ann_tag)
source_tag.append(img_tag)
ann.append(source_tag)
height = ann.find('nrows') #height
width = ann.find('ncols') #width
if height is not None and width is not None:
size_tag = newsoup.new_tag('size')
width_tag = newsoup.new_tag('width')
width_tag.string = width.string
height_tag = newsoup.new_tag('height')
height_tag.string = height.string
depth_tag = newsoup.new_tag('depth')
depth_tag.string = '3'
size_tag.append(width_tag)
size_tag.append(height_tag)
size_tag.append(depth_tag)
ann.append(size_tag)
segment_tag = newsoup.new_tag('segmented')
segment_tag.string = '1'
ann.append(segment_tag)
objects = soup.find_all('object')
for obj in objects:
deleted = obj.find('deleted')
if deleted.string == '1':
continue
object_tag = newsoup.new_tag('object')
name = obj.find('name').string
name_tag = newsoup.new_tag('name')
name_tag.string = name
pose_tag = newsoup.new_tag('pose')
pose_tag.string = 'Unspecified'
trunc_tag = newsoup.new_tag('truncated')
trunc_tag.string = '0'
difficult_tag = newsoup.new_tag('difficult')
difficult_tag.string = '0'
bndbox_tag = newsoup.new_tag('bndbox')
x_list = []
y_list = []
for x in obj.find_all('x'):
x_list.append(int(x.string))
for y in obj.find_all('y'):
y_list.append(int(y.string))
x_max, x_min = max(x_list), min(x_list)
y_max, y_min = max(y_list), min(y_list)
xmin_tag = newsoup.new_tag('xmin')
xmin_tag.string = str(x_min)
ymin_tag = newsoup.new_tag('ymin')
ymin_tag.string = str(y_min)
xmax_tag = newsoup.new_tag('xmax')
xmax_tag.string = str(x_max)
ymax_tag = newsoup.new_tag('ymax')
ymax_tag.string = str(y_max)
bndbox_tag.append(xmin_tag)
bndbox_tag.append(ymin_tag)
bndbox_tag.append(xmax_tag)
bndbox_tag.append(ymax_tag)
object_tag.append(name_tag)
object_tag.append(pose_tag)
object_tag.append(trunc_tag)
object_tag.append(difficult_tag)
object_tag.append(bndbox_tag)
ann.append(object_tag)
return newsoup.encode_contents()
final_qr += val[1:i]
try:
if len(number) != 0:
final_qr += str('"' + str(int(number)*qr_size) + '"')
except:
print('error in qr code generation')
show_error = True
final_qr += new_file[-1][1:]
with open('newqrcode.svg', 'a+') as svg:
svg.truncate(0)
svg.write(final_qr)
s = ''
with open('newqrcode.svg') as svg:
our_soup = bso(svg.read(), 'lxml')
all_child = our_soup.find('svg')
for child in all_child.findChildren():
s += str(child)[:-8] + '/>\n'
with open('svg/part2.svg', 'a+') as write_file:
write_file.truncate(0)
write_file.write(s)
svg_file_name = input('Enter the svg file name you want to save : ')
with open('omr_svg/' + svg_file_name + '.svg', 'w') as svg_file:
file = ''
with open('svg/part1.svg', 'r') as p1:
file += str(p1.read()) + '\n'
with open('svg/part2.svg', 'r') as p2:
def get_episodes(self, show_id, season):
logger.debug("https://www.tusubtitulo.com/show/{}/{}".format(
show_id, season))
r2 = self.session.get(
"https://www.tusubtitulo.com/show/{}/{}".format(show_id, season), )
r2.raise_for_status()
sopa = bso(r2.content, "lxml")
tables = sopa.find_all("tr")
seasons = [i.text for i in tables[1].find_all("a")]
if not self.is_season_available(seasons, season):
logger.debug("Season not found")
return
season_subs = []
episodes = []
for tr in range(len(tables)):
data = tables[tr].find_all("td")
title = self.title_available(data)
if title:
episodes.append(title)
source_var = self.source_separator(data)
if source_var:
inc = 1
while True:
try:
content = tables[tr + inc].find_all("td")
language = content[4].text
if "eng" in language.lower():
language = "en"
elif "esp" in language.lower():
language = "es"
else:
language = None
completed = True if not "%" in content[
5].text else False
url = content[6].find_all("a")[0].get("href")
sub_id = parse.parse_qs(
parse.urlparse(url).query)["id"][0]
lang_id = parse.parse_qs(
parse.urlparse(url).query)["lang"][0]
version_ = parse.parse_qs(
parse.urlparse(url).query)["version"][0]
download_url = (
"https://www.tusubtitulo.com/updated/{}/{}/{}".
format(lang_id, sub_id, version_))
if language and completed:
season_subs.append({
"episode_id": sub_id,
"metadata": source_var,
"download_url": download_url,
"language": language,
})
inc += 1
except IndexError:
break
final_list = []
for i in episodes:
for t in season_subs:
if i["episode_id"] == t["episode_id"]:
final_list.append({
"episode_number": i["episode_number"],
"episode_url": i["episode_url"],
"metadata": t["metadata"],
"download_url": t["download_url"],
"language": t["language"],
})
return final_list
def parse(self):
return bso(self.response.text, "html.parser")
self.engine = bso(data, "lxml")
def getSearchItems(self):
main = self.engine.find("div", attrs={"id": "main"})
searchitems = main.findChildren(recursive=False)
refineditems = []
for item in searchitems:
if item.name == "div" and "class" not in item.attrs.keys():
refineditems.append(item)
return refineditems
def dictifyItem(self, soupSearchTag):
titleH3 = soupSearchTag.find("h3", attrs={"class": "zBAuLc"})
if titleH3 == None: return None
title = titleH3.find("div").string
date = soupSearchTag.find("span", attrs={"class": "r0bn4c rQMQod"})
if date == None: return None
date = date.string
return {"title": title, "date": date}
def updateData(self, data):
self.engine = bso(data, "lxml")
#google.com/search?q=covid&num=100&pws=0&start=100
if __name__ == "__main__":
our_soup = bso(sample_content, "lxml")
first_child = our_soup.find()
print(first_child)
def post(self):
json_webhook = request.form.get('payload')
parsed_json_webhook = json.loads(json_webhook)
event = parsed_json_webhook['event']
if event not in ['media.play']:
return '', 204
media_type = parsed_json_webhook['Metadata']['type']
if media_type == 'episode':
season = parsed_json_webhook['Metadata']['parentIndex']
episode = parsed_json_webhook['Metadata']['index']
else:
season = episode = None
ids = []
for item in parsed_json_webhook['Metadata']['Guid']:
splitted_id = item['id'].split('://')
if len(splitted_id) == 2:
ids.append({splitted_id[0]: splitted_id[1]})
if not ids:
return '', 404
if media_type == 'episode':
try:
episode_imdb_id = [x['imdb'] for x in ids if 'imdb' in x][0]
r = requests.get(
'https://imdb.com/title/{}'.format(episode_imdb_id),
headers={"User-Agent": os.environ["SZ_USER_AGENT"]})
soup = bso(r.content, "html.parser")
series_imdb_id = soup.find(
'a',
{'class': re.compile(r'SeriesParentLink__ParentTextLink')
})['href'].split('/')[2]
except:
return '', 404
else:
sonarrEpisodeId = TableEpisodes.select(TableEpisodes.sonarrEpisodeId) \
.join(TableShows, on=(TableEpisodes.sonarrSeriesId == TableShows.sonarrSeriesId)) \
.where(TableShows.imdbId == series_imdb_id,
TableEpisodes.season == season,
TableEpisodes.episode == episode) \
.dicts() \
.get()
if sonarrEpisodeId:
episode_download_subtitles(
no=sonarrEpisodeId['sonarrEpisodeId'],
send_progress=True)
else:
try:
movie_imdb_id = [x['imdb'] for x in ids if 'imdb' in x][0]
except:
return '', 404
else:
radarrId = TableMovies.select(TableMovies.radarrId)\
.where(TableMovies.imdbId == movie_imdb_id)\
.dicts()\
.get()
if radarrId:
movies_download_subtitles(no=radarrId['radarrId'])
return '', 200
def getSoup():
url = 'http://www.beisbolcubano.cu/'
html = requests.get(url)
soup = bso(html.text, 'lxml')
return soup
