인프런 업로드
This commit is contained in:
@@ -30,6 +30,7 @@ for package in packages:
|
||||
import requests
|
||||
from lxml import html, etree
|
||||
from bs4 import BeautifulSoup
|
||||
from urllib import parse
|
||||
|
||||
# import snoop
|
||||
# from snoop import spy
|
||||
@@ -43,7 +44,7 @@ from framework.logger import get_logger
|
||||
# 패키지
|
||||
# from .plugin import package_name, logger
|
||||
# from anime_downloader.logic_ohli24 import ModelOhli24Item
|
||||
from .model import ModelSetting, ModelLinkkf, ModelLinkkfProgram
|
||||
from .model import ModelSetting, ModelInflearn, ModelInflearnProgram
|
||||
from .logic_queue import LogicQueue
|
||||
|
||||
#########################################################
|
||||
@@ -62,6 +63,7 @@ class LogicInflearn(object):
|
||||
session = None
|
||||
referer = None
|
||||
current_data = None
|
||||
season = "1"
|
||||
|
||||
@staticmethod
|
||||
def get_html(url):
|
||||
@@ -182,7 +184,7 @@ class LogicInflearn(object):
|
||||
ret = {}
|
||||
if LogicInflearn.current_data is not None:
|
||||
program = (
|
||||
db.session.query(ModelLinkkfProgram)
|
||||
db.session.query(ModelInflearnProgram)
|
||||
.filter_by(programcode=LogicInflearn.current_data["code"])
|
||||
.first()
|
||||
)
|
||||
@@ -219,7 +221,7 @@ class LogicInflearn(object):
|
||||
season = int(new_season)
|
||||
if LogicInflearn.current_data is not None:
|
||||
program = (
|
||||
db.session.query(ModelLinkkfProgram)
|
||||
db.session.query(ModelInflearnProgram)
|
||||
.filter_by(programcode=LogicInflearn.current_data["code"])
|
||||
.first()
|
||||
)
|
||||
@@ -292,9 +294,9 @@ class LogicInflearn(object):
|
||||
return ret
|
||||
|
||||
@staticmethod
|
||||
def get_airing_info():
|
||||
def get_lecture_list():
|
||||
try:
|
||||
url = f"{ModelSetting.get('inflearn_url')}/airing"
|
||||
url = f"{ModelSetting.get('inflearn_url')}/curation/latest?page=1"
|
||||
html_content = LogicInflearn.get_html(url)
|
||||
download_path = ModelSetting.get("download_path")
|
||||
tree = html.fromstring(html_content)
|
||||
@@ -386,45 +388,66 @@ class LogicInflearn(object):
|
||||
logger.error(traceback.format_exc())
|
||||
|
||||
@staticmethod
|
||||
def get_anime_list_info(cate, page):
|
||||
def get_lecture_list_info(cate, page):
|
||||
try:
|
||||
if cate == "ing":
|
||||
url = f"{ModelSetting.get('inflearn_url')}/airing/page/{page}"
|
||||
elif cate == "complete":
|
||||
url = f"{ModelSetting.get('inflearn_url')}/anime-list/page/{page}"
|
||||
logger.debug(f"get_anime_list_info():url >> {url}")
|
||||
url = ""
|
||||
if cate == "recent":
|
||||
# url = f"{ModelSetting.get('inflearn_url')}/curation/latest?page={page}&order={cate}"
|
||||
url = f"{ModelSetting.get('inflearn_url')}/courses?page={page}&order={cate}"
|
||||
elif cate == "rating":
|
||||
url = f"{ModelSetting.get('inflearn_url')}/courses?page={page}&order={cate}"
|
||||
elif cate == "popular":
|
||||
url = f"{ModelSetting.get('inflearn_url')}/courses?page={page}&order={cate}"
|
||||
elif cate == "seq":
|
||||
url = f"{ModelSetting.get('inflearn_url')}/courses?page={page}&order={cate}"
|
||||
logger.debug(f"get_lecture_list_info():url >> {url}")
|
||||
|
||||
html_content = LogicInflearn.get_html(url)
|
||||
download_path = ModelSetting.get("download_path")
|
||||
# logger.debug("html_content: %s", html_content)
|
||||
|
||||
tree = html.fromstring(html_content)
|
||||
tmp_items = tree.xpath('//div[@class="item"]')
|
||||
# logger.info('tmp_items:::', tmp_items)
|
||||
tmp_items = tree.xpath(
|
||||
'//div[contains(@class, "courses_card_list_body")]/div'
|
||||
)
|
||||
# logger.info("tmp_items::: %s", tmp_items)
|
||||
|
||||
data = {"ret": "success", "page": page}
|
||||
|
||||
data["total_page"] = tree.xpath('//*[@id="wp_page"]//text()')[-1]
|
||||
data["episode_count"] = len(tmp_items)
|
||||
data["episode"] = []
|
||||
data = {
|
||||
"ret": "success",
|
||||
"page": page,
|
||||
"total_page": 100,
|
||||
"episode_count": len(tmp_items),
|
||||
"episode": [],
|
||||
}
|
||||
|
||||
for item in tmp_items:
|
||||
entity = {}
|
||||
entity["link"] = item.xpath(".//a/@href")[0]
|
||||
entity["code"] = re.search(r"[0-9]+", entity["link"]).group()
|
||||
entity["title"] = item.xpath('.//span[@class="name-film"]//text()')[
|
||||
entity["code"] = entity["link"].split("/")[-1]
|
||||
entity["_code"] = item.xpath("/div/@data-productid")
|
||||
# logger.debug(item)
|
||||
# entity["code"] = 1
|
||||
entity["title"] = item.xpath('.//p[@class="course_title"]/text()')[
|
||||
0
|
||||
].strip()
|
||||
entity["image_link"] = item.xpath(
|
||||
'.//img[@class="photo"]/@data-lazy-src'
|
||||
)[0]
|
||||
entity["chapter"] = item.xpath(".//a/button/span//text()")[0]
|
||||
entity["teacher"] = item.xpath('.//div[@class="instructor"]/text()')[
|
||||
0
|
||||
].strip()
|
||||
# entity["price"] = item.xpath(
|
||||
# './/div[@class="price"]//span[@class="pay_price"]/text()'
|
||||
# )[0].strip()
|
||||
entity["price"] = item.xpath('.//div[@class="price"]/text()')
|
||||
entity["image_link"] = item.xpath('.//img[@class="swiper-lazy"]/@src')
|
||||
entity["chapter"] = entity["price"]
|
||||
# entity["chapter"] = item.xpath(".//a/button/span//text()")[0]
|
||||
# logger.info('entity:::', entity['title'])
|
||||
data["episode"].append(entity)
|
||||
|
||||
json_file_path = os.path.join(download_path, "airing_list.json")
|
||||
logger.debug("json_file_path:: %s", json_file_path)
|
||||
# json_file_path = os.path.join(download_path, "airing_list.json")
|
||||
# logger.debug("json_file_path:: %s", json_file_path)
|
||||
|
||||
with open(json_file_path, "w") as outfile:
|
||||
json.dump(data, outfile)
|
||||
# with open(json_file_path, "w") as outfile:
|
||||
# json.dump(data, outfile)
|
||||
# logger.debug("data:: %s", data)
|
||||
|
||||
return data
|
||||
|
||||
@@ -432,6 +455,73 @@ class LogicInflearn(object):
|
||||
logger.error("Exception:%s", e)
|
||||
logger.error(traceback.format_exc())
|
||||
|
||||
# @staticmethod
|
||||
# def get_lecture_list_info(cate, page):
|
||||
# try:
|
||||
# url = ""
|
||||
# if cate == "recent":
|
||||
# # url = f"{ModelSetting.get('inflearn_url')}/curation/latest?page={page}&order={cate}"
|
||||
# url = f"{ModelSetting.get('inflearn_url')}/courses?page={page}&order={cate}"
|
||||
# elif cate == "rating":
|
||||
# url = f"{ModelSetting.get('inflearn_url')}/courses?page={page}&order={cate}"
|
||||
# elif cate == "popular":
|
||||
# url = f"{ModelSetting.get('inflearn_url')}/courses?page={page}&order={cate}"
|
||||
# elif cate == "seq":
|
||||
# url = f"{ModelSetting.get('inflearn_url')}/courses?page={page}&order={cate}"
|
||||
# logger.debug(f"get_lecture_list_info():url >> {url}")
|
||||
#
|
||||
# html_content = LogicInflearn.get_html(url)
|
||||
# # logger.debug("html_content: %s", html_content)
|
||||
#
|
||||
# tree = html.fromstring(html_content)
|
||||
# tmp_items = tree.xpath(
|
||||
# '//ul[@class="tag-courses__list e-tag-courses__list"]/li'
|
||||
# )
|
||||
# # logger.info("tmp_items::: %s", tmp_items)
|
||||
#
|
||||
# data = {
|
||||
# "ret": "success",
|
||||
# "page": page,
|
||||
# "total_page": 100,
|
||||
# "episode_count": len(tmp_items),
|
||||
# "episode": [],
|
||||
# }
|
||||
#
|
||||
# for item in tmp_items:
|
||||
# entity = {}
|
||||
# entity["link"] = item.xpath(".//a/@href")[0]
|
||||
# entity["code"] = entity["link"].split("/")[-1]
|
||||
# entity["_code"] = item.attrib["data-id"]
|
||||
# # logger.debug(item)
|
||||
# # entity["code"] = 1
|
||||
# entity["title"] = item.xpath('.//div[@class="info__basic"]//h3/text()')[
|
||||
# 0
|
||||
# ].strip()
|
||||
# entity["teacher"] = item.xpath(
|
||||
# './/div[@class="info__basic"]//h4/text()'
|
||||
# )[0].strip()
|
||||
# entity["price"] = item.xpath(
|
||||
# './/div[@class="course-card__price"]/dd/text()'
|
||||
# )[0].strip()
|
||||
# entity["image_link"] = item.xpath('.//img[@class="swiper-lazy"]/@src')
|
||||
# entity["chapter"] = entity["price"]
|
||||
# # entity["chapter"] = item.xpath(".//a/button/span//text()")[0]
|
||||
# # logger.info('entity:::', entity['title'])
|
||||
# data["episode"].append(entity)
|
||||
#
|
||||
# # json_file_path = os.path.join(download_path, "airing_list.json")
|
||||
# # logger.debug("json_file_path:: %s", json_file_path)
|
||||
#
|
||||
# # with open(json_file_path, "w") as outfile:
|
||||
# # json.dump(data, outfile)
|
||||
# # logger.debug("data:: %s", data)
|
||||
#
|
||||
# return data
|
||||
#
|
||||
# except Exception as e:
|
||||
# logger.error("Exception:%s", e)
|
||||
# logger.error(traceback.format_exc())
|
||||
|
||||
@staticmethod
|
||||
def get_screen_movie_info(page):
|
||||
try:
|
||||
@@ -473,246 +563,168 @@ class LogicInflearn(object):
|
||||
logger.error("Exception:%s", e)
|
||||
logger.error(traceback.format_exc())
|
||||
|
||||
@staticmethod
|
||||
def get_complete_anilist_info(page):
|
||||
try:
|
||||
url = f"{ModelSetting.get('inflearn_url')}/anime-list/page/{page}"
|
||||
|
||||
html_content = LogicInflearn.get_html(url)
|
||||
download_path = ModelSetting.get("download_path")
|
||||
tree = html.fromstring(html_content)
|
||||
tmp_items = tree.xpath('//div[@class="item"]')
|
||||
# logger.info('tmp_items:::', tmp_items)
|
||||
|
||||
data = {"ret": "success", "page": page}
|
||||
|
||||
data["episode_count"] = len(tmp_items)
|
||||
data["episode"] = []
|
||||
|
||||
if tree.xpath('//*[@id="wp_page"]//text()'):
|
||||
data["total_page"] = tree.xpath('//*[@id="wp_page"]//text()')[-1]
|
||||
else:
|
||||
data["total_page"] = 0
|
||||
|
||||
for item in tmp_items:
|
||||
entity = {}
|
||||
entity["link"] = item.xpath(".//a/@href")[0]
|
||||
entity["code"] = re.search(r"[0-9]+", entity["link"]).group()
|
||||
entity["title"] = item.xpath('.//span[@class="name-film"]//text()')[
|
||||
0
|
||||
].strip()
|
||||
entity["image_link"] = item.xpath(
|
||||
'.//img[@class="photo"]/@data-lazy-src'
|
||||
)[0]
|
||||
# logger.info('entity:::', entity['title'])
|
||||
data["episode"].append(entity)
|
||||
|
||||
json_file_path = os.path.join(download_path, "airing_list.json")
|
||||
logger.debug("json_file_path:: %s", json_file_path)
|
||||
|
||||
with open(json_file_path, "w") as outfile:
|
||||
json.dump(data, outfile)
|
||||
|
||||
return data
|
||||
|
||||
except Exception as e:
|
||||
logger.error("Exception:%s", e)
|
||||
logger.error(traceback.format_exc())
|
||||
|
||||
@staticmethod
|
||||
def get_title_info(code):
|
||||
try:
|
||||
if (
|
||||
LogicInflearn.current_data is not None
|
||||
and LogicInflearn.current_data["code"] == code
|
||||
and LogicInflearn.current_data["ret"]
|
||||
):
|
||||
return LogicInflearn.current_data
|
||||
url = "%s/%s" % (ModelSetting.get("inflearn_url"), code)
|
||||
# logger.info(url)
|
||||
# if (
|
||||
# LogicInflearn.current_data is not None
|
||||
# and LogicInflearn.current_data["code"] == code
|
||||
# and LogicInflearn.current_data["ret"]
|
||||
# ):
|
||||
# return LogicInflearn.current_data
|
||||
url = "%s/course/%s" % (ModelSetting.get("inflearn_url"), parse.quote(code))
|
||||
logger.info(url)
|
||||
html_content = LogicInflearn.get_html(url)
|
||||
sys.setrecursionlimit(10**7)
|
||||
# logger.info(html_content)
|
||||
tree = html.fromstring(html_content)
|
||||
# tree = html.fromstring(html_content)
|
||||
# tree = etree.fromstring(
|
||||
# html_content, parser=etree.XMLParser(huge_tree=True)
|
||||
# )
|
||||
# tree1 = BeautifulSoup(html_content, "lxml")
|
||||
|
||||
soup = BeautifulSoup(html_content, "html.parser")
|
||||
# tree = etree.HTML(str(soup))
|
||||
# logger.info(tree)
|
||||
|
||||
data = {"code": code, "ret": False}
|
||||
# //*[@id="body"]/div/div[1]/article/center/strong
|
||||
# tmp = tree.xpath('/html/body/div[2]/div/div/article/center/strong'
|
||||
# )[0].text_content().strip().encode('utf8')
|
||||
# tmp = tree.xpath('//*[@id="body"]/div/div[1]/article/center/strong')[0].text_content().strip()
|
||||
# logger.info('tmp::>', tree.xpath('//div[@class="hrecipe"]/article/center/strong'))
|
||||
# tmp1 = tree.xpath("//div[contains(@id, 'related')]/ul/a")
|
||||
# tmp = tree1.find_element(By.Xpath, "//ul/a")
|
||||
tmp = soup.select("ul > a")
|
||||
|
||||
soup = BeautifulSoup(html_content, "html.parser")
|
||||
# logger.debug(soup.select_one("div.cd-header__thumbnail-cover"))
|
||||
data["poster_url"] = soup.select_one(
|
||||
"div.cd-header__thumbnail-cover div img"
|
||||
)["src"]
|
||||
data["title"] = soup.select_one("div.cd-header__title").text
|
||||
main_title = soup.select_one("div.cd-header__title").text
|
||||
# data["item_id"] = soup.select_one('meta[property="dable:item_id"]')[
|
||||
# "content"
|
||||
# ]
|
||||
# item_id = data["item_id"]
|
||||
data["save_folder"] = data["title"]
|
||||
data["season"] = "1"
|
||||
|
||||
# tmp = soup.select("ul > a")
|
||||
|
||||
# logger.debug(f"tmp1 size:=> {str(len(tmp))}")
|
||||
curriculum_content = soup.find_all("a", {"class": "cd-accordion__unit"})
|
||||
preview_path = []
|
||||
for i, elem in enumerate(curriculum_content):
|
||||
# print(elem)
|
||||
preview_path.append(elem["href"])
|
||||
# print(f"{i}. {elem['href']}")
|
||||
|
||||
try:
|
||||
tmp = (
|
||||
tree.xpath('//div[@class="hrecipe"]/article/center/strong')[0]
|
||||
.text_content()
|
||||
.strip()
|
||||
)
|
||||
except IndexError:
|
||||
tmp = tree.xpath("//article/center/strong")[0].text_content().strip()
|
||||
# 미리보기 가능 1번 동영상 뷰 페이지로 이동
|
||||
# self.getVideoInfo(preview_path[0])
|
||||
base_url = "https://www.inflearn.com"
|
||||
url = base_url + parse.quote(preview_path[0])
|
||||
logger.debug(f"url::::: {url}")
|
||||
|
||||
# print(tmp)
|
||||
# logger.info(tmp)
|
||||
match = re.compile(r"(?P<season>\d+)기").search(tmp)
|
||||
if match:
|
||||
data["season"] = match.group("season")
|
||||
else:
|
||||
data["season"] = "1"
|
||||
resData = requests.get(url, timeout=20)
|
||||
|
||||
# replace_str = f'({data["season"]}기)'
|
||||
# logger.info(replace_str)
|
||||
data["_id"] = str(code)
|
||||
data["title"] = tmp.replace(data["season"] + "기", "").strip()
|
||||
data["title"] = data["title"].replace("()", "").strip()
|
||||
data["title"] = (
|
||||
Util.change_text_for_use_filename(data["title"])
|
||||
.replace("OVA", "")
|
||||
.strip()
|
||||
)
|
||||
# logger.info(f"title:: {data['title']}")
|
||||
try:
|
||||
# data['poster_url'] = tree.xpath(
|
||||
# '//*[@id="body"]/div/div/div[1]/center/img'
|
||||
# )[0].attrib['data-src']
|
||||
if resData.url != url:
|
||||
# redirect occurred; likely symbol doesn't exist or cannot be found.
|
||||
raise requests.TooManyRedirects()
|
||||
|
||||
data["poster_url"] = tree.xpath(
|
||||
'//*[@id="body"]/div/div[1]/div[1]/center/img'
|
||||
)[0].attrib["data-lazy-src"]
|
||||
data["detail"] = [
|
||||
{
|
||||
"info": tree.xpath("/html/body/div[2]/div/div[1]/div[1]")[0]
|
||||
.text_content()
|
||||
.strip()
|
||||
}
|
||||
]
|
||||
except Exception as e:
|
||||
data["detail"] = [{"정보없음": ""}]
|
||||
data["poster_url"] = None
|
||||
resData.raise_for_status()
|
||||
|
||||
data["rate"] = tree.xpath('span[@class="tag-score"]')
|
||||
# tag_score = tree.xpath('//span[@class="taq-score"]').text_content().strip()
|
||||
tag_score = tree.xpath('//span[@class="taq-score"]')[0].text_content()
|
||||
# logger.debug(tag_score)
|
||||
tag_count = (
|
||||
tree.xpath('//span[contains(@class, "taq-count")]')[0]
|
||||
.text_content()
|
||||
.strip()
|
||||
)
|
||||
data_rate = tree.xpath('//div[@class="rating"]/div/@data-rate')
|
||||
# logger.debug("data_rate::> %s", data_rate)
|
||||
# tmp = tree.xpath('//*[@id="relatedpost"]/ul/li')
|
||||
# tmp = tree.xpath('//article/a')
|
||||
# 수정된
|
||||
# tmp = tree.xpath("//ul/a")
|
||||
tmp = soup.select("ul > a")
|
||||
# soup = BeautifulSoup(resData.text, "html.parser")
|
||||
soup = BeautifulSoup(resData.text, "html.parser")
|
||||
|
||||
# logger.debug(f"tmp size:=> {str(len(tmp))}")
|
||||
# logger.info(tmp)
|
||||
if tmp is not None:
|
||||
data["episode_count"] = str(len(tmp))
|
||||
else:
|
||||
data["episode_count"] = "0"
|
||||
items = soup.find_all("div", attrs={"class": "unit-el"})
|
||||
# print(len(items))
|
||||
lecture_list = []
|
||||
|
||||
data["episode"] = []
|
||||
# tags = tree.xpath(
|
||||
# '//*[@id="syno-nsc-ext-gen3"]/article/div[1]/article/a')
|
||||
# tags = tree.xpath("//ul/a")
|
||||
tags = soup.select("ul > a")
|
||||
# create xlsx file
|
||||
# wb = Workbook()
|
||||
# ws = wb.active # create xlsx sheet
|
||||
# ws.append(
|
||||
# ["title", "data_id", "run_time", "api_url", "file_name", "hlsUrl"]
|
||||
# )
|
||||
|
||||
# logger.info("tags", tags)
|
||||
# re1 = re.compile(r'\/(?P<code>\d+)')
|
||||
re1 = re.compile(r"\-([^-])+\.")
|
||||
|
||||
data["save_folder"] = data["title"]
|
||||
# logger.debug(f"save_folder::> {data['save_folder']}")
|
||||
temp = []
|
||||
|
||||
# print(type(items))
|
||||
program = (
|
||||
db.session.query(ModelLinkkfProgram).filter_by(programcode=code).first()
|
||||
db.session.query(ModelInflearnProgram)
|
||||
.filter_by(programcode=code)
|
||||
.first()
|
||||
)
|
||||
|
||||
if program is None:
|
||||
program = ModelLinkkfProgram(data)
|
||||
program = ModelInflearnProgram(data)
|
||||
db.session.add(program)
|
||||
db.session.commit()
|
||||
else:
|
||||
data["save_folder"] = program.save_folder
|
||||
data["season"] = program.season
|
||||
|
||||
idx = 1
|
||||
for t in tags:
|
||||
entity = {
|
||||
"_id": data["code"],
|
||||
"program_code": data["code"],
|
||||
"program_title": data["title"],
|
||||
"save_folder": Util.change_text_for_use_filename(
|
||||
data["save_folder"]
|
||||
),
|
||||
"title": t.text.strip(),
|
||||
# "title": t.text_content().strip(),
|
||||
}
|
||||
# entity['code'] = re1.search(t.attrib['href']).group('code')
|
||||
for idx, item in enumerate(items):
|
||||
#
|
||||
temp1 = {}
|
||||
print("idx::", idx)
|
||||
data_id = item["data-id"]
|
||||
|
||||
# logger.debug(f"title ::>{entity['title']}")
|
||||
run_time = ""
|
||||
title = item.find("div", attrs={"class": "title"}).get_text()
|
||||
if item.find("span", {"class": "runtime"}) is not None:
|
||||
run_time = item.find("span", {"class": "runtime"}).get_text()
|
||||
api_url = f"{base_url}/api/course/{code}/lecture/{data_id}"
|
||||
|
||||
# 고유id임을 알수 없는 말도 안됨..
|
||||
# 에피소드 코드가 고유해야 상태값 갱신이 제대로 된 값에 넣어짐
|
||||
p = re.compile(r"([0-9]+)화?")
|
||||
m_obj = p.match(entity["title"])
|
||||
# logger.info(m_obj.group())
|
||||
# entity['code'] = data['code'] + '_' +str(idx)
|
||||
temp1["season"] = "1"
|
||||
LogicInflearn.season = "1"
|
||||
# logger.debug(api_url)
|
||||
m3u8_info = LogicInflearn.getM3u8_info(
|
||||
api_url, LogicInflearn.season, idx
|
||||
)
|
||||
# print(api_url)
|
||||
# print('type::::', type(m3u8_url))
|
||||
logger.debug(m3u8_info)
|
||||
# ws.append(
|
||||
# [
|
||||
# title,
|
||||
# data_id,
|
||||
# run_time,
|
||||
# api_url,
|
||||
# m3u8_info["name"],
|
||||
# m3u8_info["hlsUrl"],
|
||||
# ]
|
||||
# )
|
||||
|
||||
episode_code = None
|
||||
# logger.debug(f"m_obj::> {m_obj}")
|
||||
if m_obj is not None:
|
||||
episode_code = m_obj.group(1)
|
||||
entity["code"] = data["code"] + episode_code.zfill(4)
|
||||
else:
|
||||
entity["code"] = data["code"]
|
||||
# temp.append(title, data_id, run_time, api_url,m3u8_info['name'], m3u8_info['hlsUrl'])
|
||||
# temp1['title'] = title
|
||||
temp1["save_folder"] = Util.change_text_for_use_filename(
|
||||
data["save_folder"]
|
||||
)
|
||||
|
||||
# logger.info('episode_code', episode_code)
|
||||
# entity["url"] = t.attrib["href"]
|
||||
entity["url"] = t["href"]
|
||||
entity["season"] = data["season"]
|
||||
# logger.debug(temp1["save_folder"])
|
||||
|
||||
# 저장경로 저장
|
||||
tmp_save_path = ModelSetting.get("download_path")
|
||||
if ModelSetting.get("auto_make_folder") == "True":
|
||||
program_path = os.path.join(tmp_save_path, entity["save_folder"])
|
||||
entity["save_path"] = program_path
|
||||
program_path = os.path.join(tmp_save_path, temp1["save_folder"])
|
||||
temp1["save_path"] = program_path
|
||||
if ModelSetting.get("inflearn_auto_make_season_folder"):
|
||||
entity["save_path"] = os.path.join(
|
||||
entity["save_path"], "Season %s" % int(entity["season"])
|
||||
temp1["save_path"] = os.path.join(
|
||||
temp1["save_path"], "Season %s" % int(temp1["season"])
|
||||
)
|
||||
|
||||
data["episode"].append(entity)
|
||||
entity["image"] = data["poster_url"]
|
||||
temp1["title"] = title
|
||||
temp1["data_id"] = data_id
|
||||
temp1["item_id"] = m3u8_info["data_id"]
|
||||
temp1["code"] = temp1["item_id"]
|
||||
temp1["run_time"] = run_time
|
||||
temp1["api_url"] = api_url
|
||||
temp1["name"] = m3u8_info["name"]
|
||||
temp1["filename"] = m3u8_info["filename"]
|
||||
# logger.debug(temp1["name"])
|
||||
# logger.debug(temp1["filename"])
|
||||
temp1["url"] = m3u8_info["hlsUrl"]
|
||||
# temp1["url"] = m3u8_info["hlsUrl"]
|
||||
temp1["size"] = m3u8_info["size"]
|
||||
temp.append(temp1)
|
||||
|
||||
# entity['title'] = t.text_content().strip().encode('utf8')
|
||||
|
||||
# entity['season'] = data['season']
|
||||
# logger.debug(f"save_folder::2> {data['save_folder']}")
|
||||
entity["filename"] = LogicInflearn.get_filename(
|
||||
data["save_folder"], data["season"], entity["title"]
|
||||
)
|
||||
idx = idx + 1
|
||||
data["ret"] = True
|
||||
# print(temp)
|
||||
# logger.info('data', data)
|
||||
# LogicInflearn.current_data = temp
|
||||
data["episode"] = temp
|
||||
LogicInflearn.current_data = data
|
||||
|
||||
# srt 파일 처리
|
||||
# logger.debug(data)
|
||||
|
||||
return data
|
||||
except Exception as e:
|
||||
@@ -728,6 +740,79 @@ class LogicInflearn(object):
|
||||
data["ret"] = "error"
|
||||
return data
|
||||
|
||||
@staticmethod
|
||||
def getM3u8_info(url, season, idx):
|
||||
data_id = ""
|
||||
m3u8_url = ""
|
||||
name = ""
|
||||
size = ""
|
||||
duration = ""
|
||||
filename = ""
|
||||
title = ""
|
||||
res_data = LogicInflearn.getHtml(url, "json").json()
|
||||
|
||||
# logger.info(f"getM3u8_info()::url => {url}")
|
||||
logger.info(f"getM3u8_info::url => {url}")
|
||||
# logger.debug("resData::: %s", res_data)
|
||||
try:
|
||||
if res_data["course"]["id"] is not None:
|
||||
data_id = res_data["course"]["id"]
|
||||
if res_data["course"]["id"] is not None:
|
||||
title = res_data["course"]["title"]
|
||||
if res_data["newBOX"]["video"]["name"] is not None:
|
||||
name = res_data["newBOX"]["video"]["name"]
|
||||
filename = f"{title}.{name.split('.')[0]}.S{season.zfill(2)}.E{str(idx).zfill(3)}.{name.split('.')[-1]}"
|
||||
if res_data["newBOX"]["video"]["vod_info"]["hlsUrl"] is not None:
|
||||
# logger.debug(res_data["newBOX"]["video"]["vod_info"]["hlsUrl"])
|
||||
m3u8_url = res_data["newBOX"]["video"]["vod_info"]["hlsUrl"]
|
||||
size = res_data["newBOX"]["video"]["vod_info"]["size"]
|
||||
duration = res_data["newBOX"]["video"]["vod_info"]["duration"]
|
||||
# return {
|
||||
# "name": name,
|
||||
# "hlsUrl": m3u8_url,
|
||||
# "size": size,
|
||||
# "duration": duration,
|
||||
# }
|
||||
except KeyError:
|
||||
pass
|
||||
# name = ""
|
||||
# m3u8_url = ""
|
||||
# size = None
|
||||
return {
|
||||
"data_id": data_id,
|
||||
"title": title,
|
||||
"name": name,
|
||||
"hlsUrl": m3u8_url,
|
||||
"size": size,
|
||||
"duration": duration,
|
||||
"filename": filename,
|
||||
}
|
||||
|
||||
@staticmethod
|
||||
def getHtml(url, header):
|
||||
o = parse.urlparse(url)
|
||||
# print(o)
|
||||
tmp_url = f"{o.scheme}://{o.netloc}{parse.quote(o.path)}"
|
||||
# print('tmp_url', tmp_url)
|
||||
|
||||
# if (header == 'json'):
|
||||
# resData = requests.get(tmp_url).json()
|
||||
# else:
|
||||
# resData = requests.get(tmp_url)
|
||||
|
||||
resData = requests.get(tmp_url)
|
||||
|
||||
# print('resData:::', resData)
|
||||
if (
|
||||
resData.url != tmp_url
|
||||
): # redirect occurred; likely symbol doesn't exist or cannot be found.
|
||||
raise requests.TooManyRedirects()
|
||||
# print(resHtml.text)
|
||||
|
||||
resData.raise_for_status()
|
||||
|
||||
return resData
|
||||
|
||||
@staticmethod
|
||||
def get_filename(maintitle, season, title):
|
||||
try:
|
||||
@@ -763,12 +848,13 @@ class LogicInflearn(object):
|
||||
|
||||
@staticmethod
|
||||
def get_info_by_code(code):
|
||||
logger.error("get_info_by_code: %s", code)
|
||||
logger.info(f"get_info_by_code: {code}")
|
||||
# logger.debug(LogicInflearn.current_data)
|
||||
|
||||
try:
|
||||
if LogicInflearn.current_data is not None:
|
||||
for t in LogicInflearn.current_data["episode"]:
|
||||
if t["code"] == code:
|
||||
if t["data_id"] == code:
|
||||
return t
|
||||
except Exception as e:
|
||||
logger.error("Exception:%s", e)
|
||||
@@ -790,8 +876,8 @@ class LogicInflearn(object):
|
||||
for code in whitelist_programs:
|
||||
logger.info("auto download start : %s", code)
|
||||
downloaded = (
|
||||
db.session.query(ModelLinkkf)
|
||||
.filter(ModelLinkkf.completed.is_(True))
|
||||
db.session.query(ModelInflearn)
|
||||
.filter(ModelInflearn.completed.is_(True))
|
||||
.filter_by(programcode=code)
|
||||
.with_for_update()
|
||||
.all()
|
||||
@@ -815,8 +901,39 @@ class LogicInflearn(object):
|
||||
logger.error("Exception:%s", e)
|
||||
logger.error(traceback.format_exc())
|
||||
|
||||
@staticmethod
|
||||
def download(form):
|
||||
try:
|
||||
ret = {}
|
||||
logger.debug("download call")
|
||||
# ret = None
|
||||
# options = {
|
||||
# "save_path": form["save_path"],
|
||||
# "filename": form["filename"],
|
||||
# "format": form["format"],
|
||||
# }
|
||||
logger.debug(form)
|
||||
# Todo:
|
||||
# tmp = LogicQueue.add_queue(form.to_dict())
|
||||
tmp = LogicQueue.add_youtube_queue(form.to_dict())
|
||||
|
||||
logger.debug("add_queue : tmp >> %s", tmp)
|
||||
# ret["ret"] = "success" if tmp else "fail"
|
||||
ret["ret"] = tmp
|
||||
return ret
|
||||
except Exception as e:
|
||||
logger.error("Exception:%s", e)
|
||||
logger.error(traceback.format_exc())
|
||||
|
||||
@staticmethod
|
||||
def reset_db() -> bool:
|
||||
db.session.query(ModelLinkkf).delete()
|
||||
db.session.query(ModelInflearn).delete()
|
||||
db.session.commit()
|
||||
return True
|
||||
|
||||
@staticmethod
|
||||
def get_excel_info():
|
||||
_path_dir = "/WD/Users/yommi/Work/fastapi/app/inflearn_xlsx"
|
||||
file_list = os.listdir(_path_dir)
|
||||
# logger.debug(file_list)
|
||||
return file_list
|
||||
|
||||
Reference in New Issue
Block a user