def multipleDownload(driver, listFileName=""):
num = 0
total_download = 0
while (1):
[count, id] = count_file_lines_and_first_line(listFileName)
if count == 0:
break
total_download = total_download + 1
print("############# 다운로드 갯수 / 남은 갯수 [%d / %d] ###############" %
(total_download, count))
print("ID : %s" % (id))
config = Config()
comicsDownload(driver, id, config.getDownloadPath())
saveListFile(listFileName, id)
print("Done.....")
def chapterListParser(driver, mangaId):
# 만화의 챕터 목록 가져 오기
c = Config()
url = c.getDomain() + base_url + mangaId
publish_type = ""
tags = []
author = ""
wait = WebDriverWait(driver, 10)
try:
driver.get(url)
wait.until(
EC.presence_of_element_located(
(By.CSS_SELECTOR, '.control-sidebar-bg')))
driver.execute_script("window.stop();")
except Exception:
reconnect(driver)
return chapterListParser(driver, mangaId)
chapterList = []
valid = True
chapterList, valid = parseChaterList(driver)
if len(chapterList) == 0 and valid == True:
retry_wait(6, "[도서 목록] ")
chapterList, valid = parseChaterList(driver)
if len(chapterList) == 0:
return chapterListParser(driver, mangaId)
if not valid:
print("잘 못 된 URL입니다.")
return [], publish_type, tags, author
html = driver.page_source
bs = BeautifulSoup(html, "html.parser")
publish_type = publishType(bs)
tags = publishTags(bs)
author = publishAuthor(bs)
title = publishTitle(bs)
data = []
for slot in reversed(chapterList):
text = slot.getText().strip()
text = pathName(text)
data.append({"title": text, "href": slot["href"]})
return data, publish_type, tags, author, title
def filterDownloadedList(folerList, driver, page):
c = Config()
wait = WebDriverWait(driver, 30)
print(LIST_URL % (c.getDomain(), page))
driver.get(LIST_URL % (c.getDomain(), page))
wait.until(
EC.presence_of_element_located((By.CSS_SELECTOR, '#thema_wrapper')))
driver.execute_script("window.stop();")
updateList = parseList(folerList, driver)
# if len(updateList) == 0:
# retry_wait(7, "[업데이트목록] ")
# updateList = parseList(folerList, driver)
# if len(updateList) == 0:
# return filterDownloadedList(folerList, driver, page)
return updateList
def arguments():
# 외부 파라미터 받기
isUpdate = False
isUpdateAll = False
updateSize = 3
downloadFile = ""
listSize = 0
try:
opts, _ = getopt.getopt(sys.argv[1:], "c:s:d:l:uh:ah", [
"help", "all", "update", "config=", "size=", "download=", "list="
])
except getopt.GetoptError as err:
print(str(err))
print("")
usage()
sys.exit(2)
defaultIni = "manatoki.ini"
if os.path.exists(defaultIni):
config = Config()
config.loadConfig(defaultIni)
else:
print("ERROR: Cant not find config.ini")
exit()
for opt, arg in opts:
if opt in ("-h", "--help"):
usage()
sys.exit()
elif opt in ("-u", "--update"):
isUpdate = True
elif opt in ("-a", "--all"):
isUpdateAll = True
elif opt in ("-s", "--size"):
updateSize = int(arg)
elif opt in ("-d", "--download"):
downloadFile = arg
elif opt in ("-l", "--list"):
listSize = arg
return isUpdate, isUpdateAll, updateSize, downloadFile, listSize
def addClipToText(str):
global clip
if (clip == str):
return
config = Config()
if 'manatoki' not in str:
return
clip = str
# q = parse_qs(urlparse(str).query).get('manga_id')
a = clip.split('/')
last = a[len(a) - 1].split('?')
id = last[0]
print("ID : " + id)
f = open("list.txt", "a")
f.write(id + "\r")
f.close()
saveListFile(listFileName, id)
print("Done.....")
if __name__ == '__main__':
multiprocessing.freeze_support() # ! 꼭 바로 다음줄에 넣어 줘야 한다.
isUpdate, isUpdateAll, updateSize, downloadFile, listSize = arguments()
# if int(listSize) > 0:
# getComicsList(int(listSize))
# exit(1)
driver = None
config = Config()
if isUpdate:
# 업데이트 일 경우
driver = driver_init()
updatedList = getUpdateList(driver, updateSize)
save_update_list(downloadFile, updatedList)
multipleDownload(driver, downloadFile)
elif isUpdateAll:
driver = driver_init()
# updatedList = checkAllDownload()
# multipleDownload(driver, updatedList)
elif downloadFile != "":
# 파일에서 다운로드 목록 확인
driver = driver_init()
multipleDownload(driver, downloadFile)
def loadConfig():
defaultIni = "manatoki.ini"
if os.path.exists(defaultIni):
config = Config()
config.loadConfig(defaultIni)
print(config.getDomain())
def comicsDownload(driver, mangaId, downloadFolder):
# 만화책에서 이미지 목록을 가져 와서 다운로드 하기
chaterList, public_type, tags, author, title = chapterListParser(
driver, mangaId)
global imageDownloadTryCount
if len(chaterList) == 0:
print("[Error] 이미지를 찾을 수 없습니다. 타이틀을 확인 해 주세요.")
return
titlePath = os.path.join(downloadFolder, pathName(title))
pathlib.Path(titlePath).mkdir(parents=True, exist_ok=True)
os.utime(pathlib.Path(titlePath), None)
skip_num = 0
saveData = loadJsonFile(os.path.join(titlePath, "data.json"))
if saveData:
skip_num = int(saveData["skip"])
num = 1
for d in chaterList:
c = Config()
url = d["href"]
if skip_num >= num:
print("[" + str(num) + "/" + str(len(chaterList)) + "] 패스 : " +
d["title"],
end="\r")
num = num + 1
continue
savePath = saveFolderPath(titlePath, num)
print(" " * 80, end="\r")
print("[" + str(num) + "/" + str(len(chaterList)) + "] 다운로드 : " +
d["title"])
num = num + 1
if os.path.exists(savePath + "." +
c.getFileExtension()) or os.path.exists(savePath +
".zip"):
print(" 이미 압축한 파일 :" + d["title"])
continue
print(" Get image list by url..", end="\r")
imageDownloadTryCount = 0
images, chapter, seed = getImageList(driver, url)
print(" Download images.. ", end="\r")
if len(images) == 0:
print(" 이미지를 찾을 수 없습니다. 패스")
continue
imagesDownload(d["title"], savePath, images, chapter, seed)
# 최근 받은 파일을 JSON으로 저장하기
json = {
'author': author,
'skip': num - 1,
'title': title,
'public_type': public_type,
'tags': tags,
'id': mangaId
}
saveJsonFile(os.path.join(titlePath, "data.json"), json)
# 완결인 책자를 별도로 저장해 준다.
if public_type == "완결" or public_type == "단편":
print("#" * 80)
print("#" * 2 + " 완결: " + title)
print("#" * 80)
title = pathName(title)
tar = os.path.join("complete", title)
pathlib.Path(os.path.join("complete")).mkdir(parents=True,
exist_ok=True)
if os.path.exists(tar):
shutil.rmtree(tar, ignore_errors=True)
shutil.move(titlePath, tar)
shutil.rmtree(titlePath, ignore_errors=True)
print("[*] Download Complete")