user01/CollectMangaInfo
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Update DataClass.py, GetArc_Hitomi.py, and 2 more files...

Browse Source 
작업한거 일단 커밋. 딱히 기능을 추가한건 없지만, 정리는 조금 했다. 정리 더 해야 하는데, 윈도우에서 작업하려고....커밋!!
This commit is contained in:
Lee Young Hoon
2025-01-28 17:45:03 +09:00
parent 6fe1cf8da0
commit 07ad09bb50
4 changed files with 105 additions and 41 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
DataClass.py
View File

@@ -14,7 +14,10 @@ class CBZInfo:
self.tags = set()
def __str__(self):
return f"{self.title} by {self.author} ({self.publication_year})"
strArtists = ", ".join(self.artists)
strTags = ", ".join(self.tags)
return f"ID : {self.gallery_id} - {self.title} by {strArtists} - #{strTags}"
def AddTag(self, name):
self.tags.add(name)

59
GetArc_Hitomi.py
View File

@@ -5,6 +5,8 @@ from selenium.webdriver.support import expected_conditions as EC
from selenium.common.exceptions import TimeoutException
from bs4 import BeautifulSoup
import time
import UtilPack as util
import DataClass as info
@@ -13,15 +15,16 @@ import DataClass as info
def GetSearchResult(searchWord):
url = getSiteUrl(searchWord)
util.DbgOut("Hitomi : " + url)
util.DbgOut("Hitomi : " + url, True)
driver = webdriver.Chrome()
driver.get(url)
# 웹페이지가 로드될 때까지 기다리기
try:
WebDriverWait(driver, 30).until(
EC.presence_of_element_located((By.CLASS_NAME, 'lillie'))
WebDriverWait(driver, 10).until(
#EC.presence_of_element_located((By.CLASS_NAME, 'lillie'))
lambda d: d.execute_script("return document.readyState") == "complete"
)
except TimeoutException:
util.DbgOut("페이지가 로드되지 않았거나 요소를 찾을 수 없습니다.")
@@ -29,21 +32,49 @@ def GetSearchResult(searchWord):
return
strContent = driver.page_source
listRet = parseMangaInfos(strContent)
for Idx in range(len(listRet)):
print(f"{Idx} : {listRet[Idx]}")
driver.quit()
parseMangaInfos(strContent)
def GetListSearchResult(list_ID):
driver = webdriver.Chrome()
pass
# 웹페이지가 로드될 때까지 기다리기
try:
for id in list_ID:
url = getSiteUrl(id)
util.DbgOut("Hitomi : " + url, True)
driver.get(url)
WebDriverWait(driver, 10).until(
lambda d: d.execute_script("return document.readyState") == "complete"
)
time.sleep(2)
strContent = driver.page_source
listRet = parseMangaInfos(strContent)
for Idx in range(len(listRet)):
print(f"{Idx} : {listRet[Idx]}")
except Exception as e:
util.DbgOut("Hitomi Loading Error : ", e)
finally:
driver.quit()
#
def getSiteUrl(searchWord):
strRet = "https://hitomi.la/"
if False == util.IsEmptyStr(searchWord):
if False == searchWord.isdigit():
strRet = strRet + "search.html?" + searchWord
else:
strRet = strRet + "galleries/" + searchWord + ".html"
if False == searchWord.isdigit():
strRet = f"{strRet}search.html?{searchWord}"
else:
strRet = f"{strRet}galleries/{searchWord}.html"
return strRet
@@ -58,7 +89,7 @@ def parseMangaInfos(html_doc):
listDJ = djParse(element)
listDJs.extend(listDJ)
print(len(listDJs))
return listDJs
def djParse(soup_element):
@@ -83,8 +114,8 @@ def djTitleParse(input_element):
a_tag = element.find('a')
url = a_tag.get('href')
util.DbgOut("title : " + title)
util.DbgOut("URl : " + url)
#util.DbgOut("title : " + title)
#util.DbgOut("URl : " + url)
return info.CBZInfo(title, url)
@@ -127,7 +158,7 @@ def djDescParse(input_element, retPtr):
outMsg += f" {tag_name} {tag_url}\r\n"
util.DbgOut(outMsg)
#util.DbgOut(outMsg)
#
if "Series" == tds[0]:

62
UI.py
View File

@@ -4,6 +4,7 @@ import UtilPack as util
import MgrCalibreDB as calDB
import MgrCalibreLibs as calLib
import pupildata as pupil
import GetArc_Hitomi as hitomi
from io import BytesIO
@@ -131,36 +132,48 @@ class MyApp(QMainWindow):
def on_click_SrcAdd(self):
# 폴더 선택 창을 띄움
folder_path = QFileDialog.getExistingDirectory(self, '폴더 선택', '')
if None == folder_path or True == util.IsEmptyStr(folder_path):
return
# 소스 폴더 목록에 추가
self.list_SrcPath.addItem(folder_path)
self.AddSourceFoldertoList(folder_path)
#캘리버 서재 폴더인가?
def AddSourceFoldertoList(self, folder_path):
#캘리버 서재 DB 파일을 먼저 확인
pathCalDB = os.path.join( folder_path, "metadata.db")
if True == os.path.exists(pathCalDB):
db = calDB.MgrCalibreDB(pathCalDB)
db.init()
listBooks = db.GetBookListforUI_ArcList()
for book in listBooks:
# 이름은 폴더/DB 파일이름
FolderName = util.GetParentDirName(folder_path, 0)
item = QListWidgetItem(f"{FolderName}/{book[0]}")
self.AddSourceCalibreDB(pathCalDB)
else:
self.AddSourceFolderContents(folder_path)
bookpath = os.path.join(folder_path, book[1])
listfiles = util.FindFileFromExt(bookpath, "cbz")
if 0 < len(listfiles):
bookpath = os.path.join(bookpath, listfiles[0])
item.setData(Qt.UserRole, bookpath)
self.list_ArcList.addItem(item)
def AddSourceCalibreDB(self, pathCalDB):
db = calDB.MgrCalibreDB(pathCalDB)
if None == db:
return
db.init()
listBooks = db.GetBookListforUI_ArcList()
for book in listBooks:
# 이름은 폴더/DB 파일이름
FolderName = util.GetParentDirName(pathCalDB, 0)
item = QListWidgetItem(f"{FolderName}/{book[0]}")
bookpath = os.path.join(pathCalDB, book[1])
listfiles = util.FindFileFromExt(bookpath, "cbz")
if 0 < len(listfiles):
bookpath = os.path.join(bookpath, listfiles[0])
item.setData(Qt.UserRole, bookpath)
self.list_ArcList.addItem(item)
return
def AddSourceFolderContents(self, folder_path):
# 폴더 내의 자식 폴더 목록을 가져온다.
listFolders = util.ListSubDirectories(folder_path)
listFolders.append(folder_path)
@@ -198,7 +211,6 @@ class MyApp(QMainWindow):
item.setData(Qt.UserRole, folder)
self.list_ArcList.addItem(item)
return
def on_click_SrcDel(self):
items = self.list_SrcPath.selectedItems()
@@ -214,7 +226,21 @@ class MyApp(QMainWindow):
def on_click_SrcRead(self):
pass
list_id = []
for idx in range(self.list_ArcList.count()):
item = self.list_ArcList.item(idx)
# 일단 파일 이름에 포함된 Hitomi ID 를 추출해 낸다.
results = util.GetTextInBrakets(item.text())
if 0 >= len(results):
continue
if False == results[0].isdigit() or 0 >= int(results[0]):
continue
list_id.append(results[0])
hitomi.GetListSearchResult(list_id)
def on_Item_SelChanged_listArc(self):

6
UtilPack.py
View File

@@ -1,4 +1,5 @@
import os
import re
import time
import uuid
import rarfile
@@ -16,7 +17,8 @@ listDbgStr = []
#
def IsEmptyStr(string):
return 0 == len(string.strip())
temp = f"{string}"
return 0 == len(temp.strip())
#
@@ -304,3 +306,5 @@ def UUIDGenName(SeedName):
namespace_uuid = uuid.uuid5(uuid.NAMESPACE_DNS, SeedName)
return namespace_uuid
def GetTextInBrakets(text):
return re.findall(r'\[(.*?)\]', text)