再也不用花錢(qián)買(mǎi)漫畫(huà)!Python爬取某漫畫(huà)的腳本及源碼
發(fā)布日期：2022-03-14 13:31 | 文章來(lái)源：腳本之家
一、工具
- python3
- 第三方類庫(kù)requests
- python3-pyqt5(GUI依賴，不用GUI可不裝)
ubuntu系列系統(tǒng)使用以下命令安裝依賴：
URL格式: 漫畫(huà)首頁(yè)的URL，如http://m.ac.qq.com/Comic/view/id/518333(移動(dòng)版) 或 http://ac.qq.com/Comic/comicInfo/id/17114, http://ac.qq.com/naruto(PC版)
注意: 火影忍者彩漫需要訪問(wèn)m.ac.qq.com搜索火影忍者，因?yàn)镻C端頁(yè)面火影忍者彩漫和黑白漫畫(huà)是一個(gè)id一個(gè)url。
二、命令行幫助
usage: getComic.py [-h] [-u URL] [-p PATH] [-d] [-l LIST] *下載騰訊漫畫(huà)，僅供學(xué)習(xí)交流，請(qǐng)勿用于非法用途* 空參運(yùn)行進(jìn)入交互式模式運(yùn)行。 optional arguments: -h, --helpshow this help message and exit -u URL, --url URL 要下載的漫畫(huà)的首頁(yè)，可以下載以下類型的url: http://ac.qq.com/Comic/comicInfo/id/511915http://m.ac.qq.com/Comic/comicInfo/id/505430http://pad.ac.qq.com/Comic/comicInfo/id/505430http://ac.qq.com/naruto -p PATH, --path PATH 漫畫(huà)下載路徑。 默認(rèn): /home/fengyu/tencent_comic -d, --dir 將所有圖片下載到一個(gè)目錄(適合騰訊漫畫(huà)等軟件連看使用) -l LIST, --list LIST 要下載的漫畫(huà)章節(jié)列表，不指定則下載所有章節(jié)。格式范例: N - 下載具體某一章節(jié)，如-l 1, 下載第1章N,N... - 下載某幾個(gè)不連續(xù)的章節(jié)，如 "-l 1,3,5", 下載1,3,5章N-N... - 下載某一段連續(xù)的章節(jié)，如 "-l 10-50", 下載[10,50]章雜合型 - 結(jié)合上面所有的規(guī)則，如 "-l 1,3,5-7,11-111"
三、GUI預(yù)覽效果
支持不連續(xù)的章節(jié)選擇下載
windows預(yù)覽效果：
deepin/Linux 預(yù)覽效果：
四、全部源碼
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):
'''自定義錯(cuò)誤碼:
1: URL不正確
2: URL無(wú)法跳轉(zhuǎn)為移動(dòng)端URL
3: 中斷下載'''
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('請(qǐng)輸入正確的url！具體支持的url請(qǐng)?jiān)诿钚休斎?h|--help參數(shù)查看幫助文檔。')
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('無(wú)法自動(dòng)跳轉(zhuǎn)移動(dòng)端URL，請(qǐng)進(jìn)入http://m.ac.qq.com，找到'
'該漫畫(huà)地址。\n'
'地址應(yīng)該像這樣: '
'http://m.ac.qq.com/Comic/comicInfo/id/xxxxx (xxxxx為整數(shù))')
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'] #統(tǒng)計(jì)圖片數(shù)量
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('該集漫畫(huà)共計(jì){}張圖片'.format(count))
i = 1
for imgUrl in imgUrlList:
print('\r正在下載第{}張圖片...'.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
#目標(biāo)文件存在就跳過(guò)下載
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 chunksf.write(chunk)f.flush()
except (KeyboardInterrupt, SystemExit):
print('\n\n中斷下載，刪除未下載完的文件！')
if os.path.isfile(imgPath):
os.remove(imgPath)
raise ErrorCode(3)
print('完畢!\n')
def parseLIST(lst):
'''解析命令行中的-l|--list參數(shù)，返回解析后的章節(jié)列表'''
legalListRE = re.compile(r'^\d+([,-]\d+)*$')
if not legalListRE.match(lst):
raise LISTFormatError(lst + ' 不匹配正則: ' + r'^\d+([,-]\d+)*$')
#先逗號(hào)分割字符串，分割后的字符串再用短橫杠分割
parsedLIST = []
sublist = lst.split(',')
numRE = re.compile(r'^\d+$')
for sub in sublist:
if numRE.match(sub):
if int(sub) > 0: #自動(dòng)忽略掉數(shù)字0
parsedLIST.append(int(sub))
else:
print('警告: 參數(shù)中包括不存在的章節(jié)0，自動(dòng)忽略')
else:
splitnum = list(map(int, sub.split('-')))
maxnum = max(splitnum)
minnum = min(splitnum) #min-max或max-min都支持
if minnum == 0:
minnum = 1#忽略數(shù)字0
print('警告: 參數(shù)中包括不存在的章節(jié)0，自動(dòng)忽略')
parsedLIST.extend(range(minnum, maxnum+1))
parsedLIST = sorted(set(parsedLIST)) #按照從小到大的順序排序并去重
return parsedLIST
def main(url, path, lst=None, one_folder=False):
'''url: 要爬取的漫畫(huà)首頁(yè)。 path: 漫畫(huà)下載路徑。 lst: 要下載的章節(jié)列表(-l|--list后面的參數(shù))'''
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('漫畫(huà)名: {}'.format(comicName))
print('簡(jiǎn)介: {}'.format(comicIntrd))
print('章節(jié)數(shù): {}'.format(count))
print('章節(jié)列表:')
try:
print('\n'.join(contentNameList))
except Exception:
print('章節(jié)列表包含無(wú)法解析的特殊字符\n')
forbiddenRE = re.compile(r'[\\/":*?<>|]') #windows下文件名非法字符\ / : * ? " < > |
comicName = re.sub(forbiddenRE, '_', comicName) #將windows下的非法字符一律替換為_(kāi)
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('警告: 章節(jié)總數(shù) {} ,''參數(shù)中包含過(guò)大數(shù)值,''自動(dòng)忽略'.format(len(contentList)))
break
contentNameList[i - 1] = re.sub(forbiddenRE, '_', contentNameList[i - 1]) #將windows下的非法字符一律替換為_(kāi)
contentPath = os.path.join(comicPath, '第{0:0>4}話-{1}'.format(i, contentNameList[i - 1]))
try:
print('正在下載第{0:0>4}話: {1}'.format(i, contentNameList[i -1]))
except Exception:
print('正在下載第{0:0>4}話: {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='*下載騰訊漫畫(huà)，僅供學(xué)習(xí)交流，請(qǐng)勿用于非法用途*\n'
'空參運(yùn)行進(jìn)入交互式模式運(yùn)行。')
parser.add_argument('-u', '--url', help='要下載的漫畫(huà)的首頁(yè)，可以下載以下類型的url: \n'
'http://ac.qq.com/Comic/comicInfo/id/511915\n'
'http://m.ac.qq.com/Comic/comicInfo/id/505430\n'
'http://pad.ac.qq.com/Comic/comicInfo/id/505430\n'
'http://ac.qq.com/naruto')
parser.add_argument('-p', '--path', help='漫畫(huà)下載路徑。 默認(rèn): {}'.format(defaultPath),
default=defaultPath)
parser.add_argument('-d', '--dir', action='store_true', help='將所有圖片下載到一個(gè)目錄(適合騰訊漫畫(huà)等軟件連看使用)')
parser.add_argument('-l', '--list', help=("要下載的漫畫(huà)章節(jié)列表，不指定則下載所有章節(jié)。格式范例: \n"
"N - 下載具體某一章節(jié)，如-l 1, 下載第1章\n"
'N,N... - 下載某幾個(gè)不連續(xù)的章節(jié)，如 "-l 1,3,5", 下載1,3,5章\n'
'N-N... - 下載某一段連續(xù)的章節(jié)，如 "-l 10-50", 下載[10,50]章\n'
'雜合型 - 結(jié)合上面所有的規(guī)則，如 "-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參數(shù)不合法，請(qǐng)參考--help鍵入合法參數(shù)！')
exit(1)
if not url:
url = input('請(qǐng)輸入漫畫(huà)首頁(yè)地址: ')
path = input('請(qǐng)輸入漫畫(huà)保存路徑(默認(rèn): {}): '.format(defaultPath))
if not path:
path = defaultPath
main(url, path, lst, one_folder)
五、下載源碼
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("漫畫(huà)首頁(yè):")
self.nameLine = QLineEdit()
self.analysisButton = QPushButton("分析")
self.analysisButton.clicked.connect(self.anaysisURL)
self.nameLine.returnPressed.connect(self.analysisButton.click)
pathLineLabel = QLabel("下載路徑:")
self.pathLine = QLineEdit()
defaultPath = os.path.join(os.path.expanduser('~'), 'tencent_comic')
self.pathLine.setText(defaultPath)
self.browseButton = QPushButton("瀏覽")
self.browseButton.clicked.connect(self.getPath)
comicNameLabel = QLabel("漫畫(huà)名: ")
self.comicNameLabel = QLabel("暫無(wú)")
self.one_folder_checkbox = QCheckBox("單目錄")
comicIntroLabel = QLabel("簡(jiǎn)介: ")
self.comicIntro = QLabel("暫無(wú)")
self.comicIntro.setWordWrap(True)
chapterGroupBox = QGroupBox("章節(jié)列表:")
self.chapterListView = QListWidget(chapterGroupBox)
self.chapterListView.setSelectionMode(QAbstractItemView.ExtendedSelection)
self.chapterListView.setEnabled(False)
groupBoxLayout = QHBoxLayout(chapterGroupBox)
groupBoxLayout.addWidget(self.chapterListView)
self.downloadButton = QPushButton("下載選中")
self.statusLabel = QLabel("輸入要下載的漫畫(huà)的首頁(yè)，然后點(diǎn)分析")
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("騰訊漫畫(huà)下載")
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('下載選中')
self.chapterListView.setFocus()
def getPath(self):
path = str(QFileDialog.getExistingDirectory(self, "選擇下載目錄"))
if path:
self.pathLine.setText(path)
def anaysisURL(self):
url = self.nameLine.text()
self.downloadButton.setEnabled(False)
self.comicNameLabel.setText("暫無(wú)")
self.comicIntro.setText("暫無(wú)")
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('選擇要下載的章節(jié)后點(diǎn)擊右側(cè)按鈕')
for i in range(len(self.contentNameList)):
self.chapterListView.addItem('第{0:0>4}話-{1}'.format(i+1, self.contentNameList[i]))
self.chapterListView.item(i).setSelected(True)
self.downloadButton.setEnabled(True)
else:
self.statusLabel.setText('<font color="red">錯(cuò)誤的URL格式！請(qǐng)輸入正確的漫畫(huà)首頁(yè)地址！</font>')
except getComic.ErrorCode as e:
if e.code == 2:
self.statusLabel.setText('<font color="red">無(wú)法跳轉(zhuǎn)為移動(dòng)端URL,請(qǐng)進(jìn)入http://m.ac.qq.com找到該漫畫(huà)地址</font>')
except KeyError:
self.statusLabel.setText('<font color="red">不存在的地址</font>')
def download(self):
self.downloadButton.setText("下載中...")
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下文件名非法字符\ / : * ? " < > |
comicName = re.sub(forbiddenRE, '_', comicName) #將windows下的非法字符一律替換為_(kāi)
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 = '正在下載第{0:0>4}話: {1}...'.format(i+1, self.contentNameList[i])
print(outputString)
self.output.emit(outputString)
forbiddenRE = re.compile(r'[\\/":*?<>|]') #windows下文件名非法字符\ / : * ? " < > |
self.contentNameList[i] = re.sub(forbiddenRE, '_', self.contentNameList[i])
contentPath = os.path.join(self.comicPath, '第{0:0>4}話-{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('完畢!')
except Exception as e:
self.output.emit('<font color="red">{}</font>\n'
'遇到異常!請(qǐng)嘗試重新點(diǎn)擊下載按鈕重試'.format(e))
raise
finally:
self.finished.emit()
if __name__ == '__main__':
app = QApplication(sys.argv)
main = TencentComicDownloader()
main.show()
app.exec_()
到此這篇關(guān)于再也不用花錢(qián)買(mǎi)漫畫(huà)!Python下載某漫畫(huà)的腳本及源碼的文章就介紹到這了,更多相關(guān)Python下載漫畫(huà)內(nèi)容請(qǐng)搜索本站以前的文章或繼續(xù)瀏覽下面的相關(guān)文章希望大家以后多多支持本站！
版權(quán)聲明：本站文章來(lái)源標(biāo)注為YINGSOO的內(nèi)容版權(quán)均為本站所有，歡迎引用、轉(zhuǎn)載，請(qǐng)保持原文完整并注明來(lái)源及原文鏈接。禁止復(fù)制或仿造本網(wǎng)站，禁止在非www.sddonglingsh.com所屬的服務(wù)器上建立鏡像，否則將依法追究法律責(zé)任。本站部分內(nèi)容來(lái)源于網(wǎng)友推薦、互聯(lián)網(wǎng)收集整理而來(lái)，僅供學(xué)習(xí)參考，不代表本站立場(chǎng)，如有內(nèi)容涉嫌侵權(quán)，請(qǐng)聯(lián)系alex-e#qq.com處理。
相關(guān)文章
關(guān)注官方微信