다 시 는 돈 을 써 서 만 화 를 살 필요 가 없다!Python 은 어떤 만화 의 각본 과 소스 코드 를 기어 올 랐 다.
URL 형식:만화 첫 페이지 의 URL,예 를 들 어http://m.ac.qq.com/Comic/view/id/518333(모 바 일 버 전)또는http://ac.qq.com/Comic/comicInfo/id/17114,http://ac.qq.com/naruto(PC 버 전)
주의:화 영 닌 자 채 만 은 방문 해 야 합 니 다
m.ac.qq.com화 영 닌 자 를 검색 해 야 합 니 다.PC 엔 드 페이지 화 영 닌 자 채 만 과 흑백 만 화 는 id 하나의 url 이기 때 문 입 니 다.2.명령 행 도움
usage: getComic.py [-h] [-u URL] [-p PATH] [-d] [-l LIST]
* ， ， *
。
optional arguments:
-h, --help show this help message and exit
-u URL, --url URL ， url:
http://ac.qq.com/Comic/comicInfo/id/511915
http://m.ac.qq.com/Comic/comicInfo/id/505430
http://pad.ac.qq.com/Comic/comicInfo/id/505430
http://ac.qq.com/naruto
-p PATH, --path PATH 。 : /home/fengyu/tencent_comic
-d, --dir ( )
-l LIST, --list LIST ， 。 :
N - ， -l 1, 1
N,N... - ， "-l 1,3,5", 1,3,5
N-N... - ， "-l 10-50", [10,50]
- ， "-l 1,3,5-7,11-111"
연속 되 지 않 는 장 선택 다운로드 지원
윈도 우즈 미리 보기 효과:
deepin/Linux 미리 보기 효과:
4.모든 소스 코드
import requests
import re
import json
import os
import argparse
requestSession = requests.session()
UA = 'Mozilla/5.0 (iPad; CPU OS 5_1 like Mac OS X; en-us) \
AppleWebKit/534.46 (KHTML, like Gecko) Version/5.1 \
Mobile/9B176 Safari/7534.48.3' # ipad UA
requestSession.headers.update({'User-Agent': UA})
class ErrorCode(Exception):
''' :
1: URL
2: URL URL
3: '''
def __init__(self, code):
self.code = code
def __str__(self):
return repr(self.code)
def isLegelUrl(url):
legal_url_list = [
re.compile(r'^http://ac.qq.com/Comic/[Cc]omicInfo/id/\d+/?$'),
re.compile(r'^http://m.ac.qq.com/Comic/[Cc]omicInfo/id/\d+/?$'),
re.compile(r'^http://ac.qq.com/\w+/?$'),
re.compile(r'^http://pad.ac.qq.com/Comic/[Cc]omicInfo/id/\d+/?$')
]
for legal_url in legal_url_list:
if legal_url.match(url):
return True
return False
def getId(url):
if not isLegelUrl(url):
print(' url！ url -h|--help 。')
raise ErrorCode(1)
numRE = re.compile(r'\d+$')
id = numRE.findall(url)
if not id:
get_id_request = requestSession.get(url)
url = get_id_request.url
id = numRE.findall(url)
if not isLegelUrl(url) or not id:
print(' URL， http://m.ac.qq.com， '
' 。
'
' : '
'http://m.ac.qq.com/Comic/comicInfo/id/xxxxx (xxxxx )')
raise ErrorCode(2)
return id[0]
def getContent(id):
getComicInfoUrl = 'http://pad.ac.qq.com/GetData/getComicInfo?id={}'.format(id)
requestSession.headers.update({'Cookie': 'ac_refer=http://pad.ac.qq.com'})
requestSession.headers.update({'Referer': 'http://pad.ac.qq.com'})
getComicInfo = requestSession.get(getComicInfoUrl)
comicInfoJson = getComicInfo.text
comicInfo = json.loads(comicInfoJson)
comicName = comicInfo['title']
comicIntrd = comicInfo['brief_intrd']
getChapterListUrl = 'http://pad.ac.qq.com/GetData/getChapterList?id={}'.format(id)
getChapterList = requestSession.get(getChapterListUrl)
contentJson = json.loads(getChapterList.text)
count = contentJson['length']
sortedContentList = []
for i in range(count + 1):
for item in contentJson:
if isinstance(contentJson[item], dict) and contentJson[item].get('seq') == i:
sortedContentList.append({item: contentJson[item]})
break
return (comicName, comicIntrd, count, sortedContentList)
def getImgList(contentJson, id):
cid = list(contentJson.keys())[0]
getPicHashURL = 'http://pad.ac.qq.com/View/mGetPicHash?id={}&cid={}'.format(id, cid)
picJsonPage = requestSession.get(getPicHashURL).text
picJson = json.loads(picJsonPage)
count = picJson['pCount'] #
pHash = picJson['pHash']
sortedImgDictList = []
for i in range(1, count + 1):
for item in pHash:
if pHash[item]['seq'] == i:
sortedImgDictList.append(pHash[item])
break
imgList = []
for imgDict in sortedImgDictList:
k = imgDict['cid']
m = imgDict['pid']
j = int(id)
uin = max(j + k + m, 10001)
l = [j % 1000 // 100, j % 100, j, k]
n = '/mif800/' + '/'.join(str(j) for j in l) + '/'
h = str(m) + '.mif2'
g="http://ac.tc.qq.com/store_file_download?buid=15017&uin="+str(uin)+"&dir_path="+n+"&name="+h
imgList.append(g)
return imgList
def downloadImg(imgUrlList, contentPath, one_folder=False):
count = len(imgUrlList)
print(' {} '.format(count))
i = 1
for imgUrl in imgUrlList:
print('\r {} ...'.format(i), end = '')
if not one_folder:
imgPath = os.path.join(contentPath, '{0:0>3}.jpg'.format(i))
else:
imgPath = contentPath + '{0:0>3}.jpg'.format(i)
i += 1
#
if os.path.isfile(imgPath):
continue
try:
downloadRequest = requestSession.get(imgUrl, stream=True)
with open(imgPath, 'wb') as f:
for chunk in downloadRequest.iter_content(chunk_size=1024):
if chunk: # filter out keep-alive new chunks
f.write(chunk)
f.flush()
except (KeyboardInterrupt, SystemExit):
print('
， ！')
if os.path.isfile(imgPath):
os.remove(imgPath)
raise ErrorCode(3)
print(' !
')
def parseLIST(lst):
''' -l|--list ， '''
legalListRE = re.compile(r'^\d+([,-]\d+)*$')
if not legalListRE.match(lst):
raise LISTFormatError(lst + ' : ' + r'^\d+([,-]\d+)*$')
# ，
parsedLIST = []
sublist = lst.split(',')
numRE = re.compile(r'^\d+$')
for sub in sublist:
if numRE.match(sub):
if int(sub) > 0: # 0
parsedLIST.append(int(sub))
else:
print(' : 0， ')
else:
splitnum = list(map(int, sub.split('-')))
maxnum = max(splitnum)
minnum = min(splitnum) #min-max max-min
if minnum == 0:
minnum = 1 # 0
print(' : 0， ')
parsedLIST.extend(range(minnum, maxnum+1))
parsedLIST = sorted(set(parsedLIST)) #
return parsedLIST
def main(url, path, lst=None, one_folder=False):
'''url: 。 path: 。 lst: (-l|--list )'''
try:
if not os.path.isdir(path):
os.makedirs(path)
id = getId(url)
comicName,comicIntrd,count,contentList = getContent(id)
contentNameList = []
for item in contentList:
for k in item:
contentNameList.append(item[k]['t'])
print(' : {}'.format(comicName))
print(' : {}'.format(comicIntrd))
print(' : {}'.format(count))
print(' :')
try:
print('
'.join(contentNameList))
except Exception:
print('
')
forbiddenRE = re.compile(r'[\\/":*?<>|]') #windows \ / : * ? " < > |
comicName = re.sub(forbiddenRE, '_', comicName) # windows _
comicPath = os.path.join(path, comicName)
if not os.path.isdir(comicPath):
os.makedirs(comicPath)
print()
if not lst:
contentRange = range(1, len(contentList) + 1)
else:
contentRange = parseLIST(lst)
for i in contentRange:
if i > len(contentList):
print(' : {} ,'
' ,'
' '.format(len(contentList)))
break
contentNameList[i - 1] = re.sub(forbiddenRE, '_', contentNameList[i - 1]) # windows _
contentPath = os.path.join(comicPath, ' {0:0>4} -{1}'.format(i, contentNameList[i - 1]))
try:
print(' {0:0>4} : {1}'.format(i, contentNameList[i -1]))
except Exception:
print(' {0:0>4} : {1}'.format(i))
if not one_folder:
if not os.path.isdir(contentPath):
os.mkdir(contentPath)
imgList = getImgList(contentList[i - 1], id)
downloadImg(imgList, contentPath, one_folder)
except ErrorCode as e:
exit(e.code)
if __name__ == '__main__':
defaultPath = os.path.join(os.path.expanduser('~'), 'tencent_comic')
parser = argparse.ArgumentParser(formatter_class=argparse.RawTextHelpFormatter,
description='* ， ， *
'
' 。')
parser.add_argument('-u', '--url', help=' ， url:
'
'http://ac.qq.com/Comic/comicInfo/id/511915
'
'http://m.ac.qq.com/Comic/comicInfo/id/505430
'
'http://pad.ac.qq.com/Comic/comicInfo/id/505430
'
'http://ac.qq.com/naruto')
parser.add_argument('-p', '--path', help=' 。 : {}'.format(defaultPath),
default=defaultPath)
parser.add_argument('-d', '--dir', action='store_true', help=' ( )')
parser.add_argument('-l', '--list', help=(" ， 。 :
"
"N - ， -l 1, 1
"
'N,N... - ， "-l 1,3,5", 1,3,5
'
'N-N... - ， "-l 10-50", [10,50]
'
' - ， "-l 1,3,5-7,11-111"'))
args = parser.parse_args()
url = args.url
path = args.path
lst = args.list
one_folder = args.dir
if lst:
legalListRE = re.compile(r'^\d+([,-]\d+)*$')
if not legalListRE.match(lst):
print('LIST ， --help ！')
exit(1)
if not url:
url = input(' : ')
path = input(' ( : {}): '.format(defaultPath))
if not path:
path = defaultPath
main(url, path, lst, one_folder)
from PyQt5.QtCore import *
from PyQt5.QtWidgets import *
from PyQt5.QtGui import *
import getComic
import os
import re
import sys
class TencentComicDownloader(QWidget):
def __init__(self, parent=None):
super(TencentComicDownloader, self).__init__(parent)
nameLabel = QLabel(" :")
self.nameLine = QLineEdit()
self.analysisButton = QPushButton(" ")
self.analysisButton.clicked.connect(self.anaysisURL)
self.nameLine.returnPressed.connect(self.analysisButton.click)
pathLineLabel = QLabel(" :")
self.pathLine = QLineEdit()
defaultPath = os.path.join(os.path.expanduser('~'), 'tencent_comic')
self.pathLine.setText(defaultPath)
self.browseButton = QPushButton(" ")
self.browseButton.clicked.connect(self.getPath)
comicNameLabel = QLabel(" : ")
self.comicNameLabel = QLabel(" ")
self.one_folder_checkbox = QCheckBox(" ")
comicIntroLabel = QLabel(" : ")
self.comicIntro = QLabel(" ")
self.comicIntro.setWordWrap(True)
chapterGroupBox = QGroupBox(" :")
self.chapterListView = QListWidget(chapterGroupBox)
self.chapterListView.setSelectionMode(QAbstractItemView.ExtendedSelection)
self.chapterListView.setEnabled(False)
groupBoxLayout = QHBoxLayout(chapterGroupBox)
groupBoxLayout.addWidget(self.chapterListView)
self.downloadButton = QPushButton(" ")
self.statusLabel = QLabel(" ， ")
self.statusLabel.setWordWrap(True)
self.downloadButton.setEnabled(False)
self.downloadButton.clicked.connect(self.download)
mainLayout = QGridLayout()
mainLayout.addWidget(nameLabel, 0, 0)
mainLayout.addWidget(self.nameLine, 0, 1)
mainLayout.addWidget(self.analysisButton, 0, 2)
mainLayout.addWidget(pathLineLabel, 1, 0)
mainLayout.addWidget(self.pathLine, 1, 1)
mainLayout.addWidget(self.browseButton, 1, 2)
mainLayout.addWidget(comicNameLabel, 2, 0)
mainLayout.addWidget(self.comicNameLabel, 2, 1, 1, 2)
mainLayout.addWidget(self.one_folder_checkbox, 2, 2)
mainLayout.addWidget(comicIntroLabel, 3, 0)
mainLayout.addWidget(self.comicIntro, 3, 1, 1, 2)
mainLayout.addWidget(chapterGroupBox, 4, 0, 1, 3)
mainLayout.addWidget(self.downloadButton, 5, 2)
mainLayout.addWidget(self.statusLabel, 5, 0, 1, 2)
self.setLayout(mainLayout)
self.setWindowTitle(" ")
self.setGeometry(400, 300, 800, 500)
def setStatus(self, status):
self.statusLabel.setText(status)
def enableWidget(self, enable):
widgets_list = [
self.downloadButton,
self.nameLine,
self.pathLine,
self.chapterListView,
self.analysisButton,
self.browseButton,
self.one_folder_checkbox
]
for widget in widgets_list:
widget.setEnabled(enable)
if enable:
self.downloadButton.setText(' ')
self.chapterListView.setFocus()
def getPath(self):
path = str(QFileDialog.getExistingDirectory(self, " "))
if path:
self.pathLine.setText(path)
def anaysisURL(self):
url = self.nameLine.text()
self.downloadButton.setEnabled(False)
self.comicNameLabel.setText(" ")
self.comicIntro.setText(" ")
self.chapterListView.clear()
self.chapterListView.setEnabled(False)
try:
if getComic.isLegelUrl(url):
self.id = getComic.getId(url)
self.comicName,self.comicIntrd,self.count,self.contentList = getComic.getContent(self.id)
self.contentNameList = []
for item in self.contentList:
for k in item:
self.contentNameList.append(item[k]['t'])
self.comicNameLabel.setText(self.comicName)
self.comicIntro.setText(self.comicIntrd)
self.chapterListView.setEnabled(True)
self.downloadButton.setEnabled(True)
self.chapterListView.setFocus()
self.statusLabel.setText(' ')
for i in range(len(self.contentNameList)):
self.chapterListView.addItem(' {0:0>4} -{1}'.format(i+1, self.contentNameList[i]))
self.chapterListView.item(i).setSelected(True)
self.downloadButton.setEnabled(True)
else:
self.statusLabel.setText('<font color="red"> URL ！ ！</font>')
except getComic.ErrorCode as e:
if e.code == 2:
self.statusLabel.setText('<font color="red"> URL, http://m.ac.qq.com </font>')
except KeyError:
self.statusLabel.setText('<font color="red"> </font>')
def download(self):
self.downloadButton.setText(" ...")
one_folder = self.one_folder_checkbox.isChecked()
self.enableWidget(False)
selectedChapterList = [ item.row() for item in self.chapterListView.selectedIndexes() ]
path = self.pathLine.text()
comicName = self.comicName
forbiddenRE = re.compile(r'[\\/":*?<>|]') #windows \ / : * ? " < > |
comicName = re.sub(forbiddenRE, '_', comicName) # windows _
comicPath = os.path.join(path, comicName)
if not os.path.isdir(comicPath):
os.makedirs(comicPath)
self.downloadThread = Downloader(selectedChapterList, comicPath, self.contentList, self.contentNameList, self.id, one_folder)
self.downloadThread.output.connect(self.setStatus)
self.downloadThread.finished.connect(lambda: self.enableWidget(True))
self.downloadThread.start()
class Downloader(QThread):
output = pyqtSignal(['QString'])
finished = pyqtSignal()
def __init__(self, selectedChapterList, comicPath, contentList, contentNameList, id, one_folder=False, parent=None):
super(Downloader, self).__init__(parent)
self.selectedChapterList = selectedChapterList
self.comicPath = comicPath
self.contentList = contentList
self.contentNameList = contentNameList
self.id = id
self.one_folder = one_folder
def run(self):
try:
for i in self.selectedChapterList:
outputString = ' {0:0>4} : {1}...'.format(i+1, self.contentNameList[i])
print(outputString)
self.output.emit(outputString)
forbiddenRE = re.compile(r'[\\/":*?<>|]') #windows \ / : * ? " < > |
self.contentNameList[i] = re.sub(forbiddenRE, '_', self.contentNameList[i])
contentPath = os.path.join(self.comicPath, ' {0:0>4} -{1}'.format(i+1, self.contentNameList[i]))
if not self.one_folder:
if not os.path.isdir(contentPath):
os.mkdir(contentPath)
imgList = getComic.getImgList(self.contentList[i], self.id)
getComic.downloadImg(imgList, contentPath, self.one_folder)
self.output.emit(' !')
except Exception as e:
self.output.emit('<font color="red">{}</font>
'
' ! '.format(e))
raise
finally:
self.finished.emit()
if __name__ == '__main__':
app = QApplication(sys.argv)
main = TencentComicDownloader()
main.show()
app.exec_()
이 내용에 흥미가 있습니까?
현재 기사가 여러분의 문제를 해결하지 못하는 경우 AI 엔진은 머신러닝 분석(스마트 모델이 방금 만들어져 부정확한 경우가 있을 수 있음)을 통해 가장 유사한 기사를 추천합니다:
Python의 None과 NULL의 차이점 상세 정보그래서 대상 = 속성 + 방법 (사실 방법도 하나의 속성, 데이터 속성과 구별되는 호출 가능한 속성 같은 속성과 방법을 가진 대상을 클래스, 즉 Classl로 분류할 수 있다.클래스는 하나의 청사진과 같아서 하나의 ...
텍스트를 자유롭게 공유하거나 복사할 수 있습니다.하지만 이 문서의 URL은 참조 URL로 남겨 두십시오.
CC BY-SA 2.5, CC BY-SA 3.0 및 CC BY-SA 4.0에 따라 라이센스가 부여됩니다.
좋은 웹페이지 즐겨찾기
