Python爬取漫画 再也不用花钱买漫画!Python爬取某漫画的脚本及源码

usage: getComic.py [-h] [-u URL] [-p PATH] [-d] [-l LIST]
 
*下载腾讯漫画，仅供学习交流，请勿用于非法用途*
空参运行进入交互式模式运行。
 
optional arguments:
  -h, --help            show this help message and exit
  -u URL, --url URL     要下载的漫画的首页，可以下载以下类型的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  漫画下载路径。 默认: /home/fengyu/tencent_comic
  -d, --dir             将所有图片下载到一个目录(适合腾讯漫画等软件连看使用)
  -l LIST, --list LIST  要下载的漫画章节列表，不指定则下载所有章节。格式范例: 
                        N - 下载具体某一章节，如-l 1, 下载第1章
                        N,N... - 下载某几个不连续的章节，如 "-l 1,3,5", 下载1,3,5章
                        N-N... - 下载某一段连续的章节，如 "-l 10-50", 下载[10,50]章
                        杂合型 - 结合上面所有的规则，如 "-l 1,3,5-7,11-111"

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):
    '''自定义错误码:
        1: URL不正确
        2: URL无法跳转为移动端URL
        3: 中断下载'''
    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('请输入正确的url！具体支持的url请在命令行输入-h|--help参数查看帮助文档。')
        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('无法自动跳转移动端URL，请进入http://m.ac.qq.com，找到'
            '该漫画地址。\n'
            '地址应该像这样: '
            'http://m.ac.qq.com/Comic/comicInfo/id/xxxxx (xxxxx为整数)')
            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']    #统计图片数量
    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('该集漫画共计{}张图片'.format(count))
    i = 1
 
    for imgUrl in imgUrlList:
        print('\r正在下载第{}张图片...'.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
        
        #目标文件存在就跳过下载
        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('\n\n中断下载，删除未下载完的文件！')
            if os.path.isfile(imgPath):
                os.remove(imgPath)
            raise ErrorCode(3)
 
    print('完毕!\n')
 
def parseLIST(lst):
    '''解析命令行中的-l|--list参数，返回解析后的章节列表'''
    legalListRE = re.compile(r'^\d+([,-]\d+)*$')
    if not legalListRE.match(lst):
        raise LISTFormatError(lst + ' 不匹配正则: ' + r'^\d+([,-]\d+)*$')
 
    #先逗号分割字符串，分割后的字符串再用短横杠分割
    parsedLIST = []
    sublist = lst.split(',')
    numRE = re.compile(r'^\d+$')
 
    for sub in sublist:
        if numRE.match(sub):
            if int(sub) > 0: #自动忽略掉数字0
                parsedLIST.append(int(sub))
            else:
                print('警告: 参数中包括不存在的章节0，自动忽略')
        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               #忽略数字0
                print('警告: 参数中包括不存在的章节0，自动忽略')
            parsedLIST.extend(range(minnum, maxnum+1))
 
    parsedLIST = sorted(set(parsedLIST)) #按照从小到大的顺序排序并去重
    return parsedLIST
 
def main(url, path, lst=None, one_folder=False):
    '''url: 要爬取的漫画首页。 path: 漫画下载路径。 lst: 要下载的章节列表(-l|--list后面的参数)'''
    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('漫画名: {}'.format(comicName))
        print('简介: {}'.format(comicIntrd))
        print('章节数: {}'.format(count))
        print('章节列表:')
        try:
            print('\n'.join(contentNameList))
        except Exception:
            print('章节列表包含无法解析的特殊字符\n')
            
        forbiddenRE = re.compile(r'[\\/":*?<>|]') #windows下文件名非法字符\ / : * ? " < > |
        comicName = re.sub(forbiddenRE, '_', comicName) #将windows下的非法字符一律替换为_
        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: 章节总数 {} ,'
                        '参数中包含过大数值,'
                        '自动忽略'.format(len(contentList)))
                break
 
            contentNameList[i - 1] = re.sub(forbiddenRE, '_', contentNameList[i - 1]) #将windows下的非法字符一律替换为_
            contentPath = os.path.join(comicPath, '第{0:0>4}话-{1}'.format(i, contentNameList[i - 1]))
 
            try:
                print('正在下载第{0:0>4}话: {1}'.format(i, contentNameList[i -1]))
            except Exception:
                print('正在下载第{0:0>4}话: {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='*下载腾讯漫画，仅供学习交流，请勿用于非法用途*\n'
                                     '空参运行进入交互式模式运行。')
    parser.add_argument('-u', '--url', help='要下载的漫画的首页，可以下载以下类型的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='漫画下载路径。 默认: {}'.format(defaultPath), 
                default=defaultPath)
    parser.add_argument('-d', '--dir', action='store_true', help='将所有图片下载到一个目录(适合腾讯漫画等软件连看使用)')
    parser.add_argument('-l', '--list', help=("要下载的漫画章节列表，不指定则下载所有章节。格式范例: \n"
                                              "N - 下载具体某一章节，如-l 1, 下载第1章\n"
                                              'N,N... - 下载某几个不连续的章节，如 "-l 1,3,5", 下载1,3,5章\n'
                                              'N-N... - 下载某一段连续的章节，如 "-l 10-50", 下载[10,50]章\n'
                                              '杂合型 - 结合上面所有的规则，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参数不合法，请参考--help键入合法参数！')
            exit(1)
 
    if not url:
        url = input('请输入漫画首页地址: ')
        path = input('请输入漫画保存路径(默认: {}): '.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("漫画首页:")
 
        self.nameLine = QLineEdit()
 
        self.analysisButton = QPushButton("分析")
        self.analysisButton.clicked.connect(self.anaysisURL)
        self.nameLine.returnPressed.connect(self.analysisButton.click)
 
        pathLineLabel = QLabel("下载路径:")
        self.pathLine = QLineEdit()
        defaultPath = os.path.join(os.path.expanduser('~'), 'tencent_comic')
        self.pathLine.setText(defaultPath)
        
        self.browseButton = QPushButton("浏览")
        self.browseButton.clicked.connect(self.getPath)
 
        comicNameLabel = QLabel("漫画名: ")
        self.comicNameLabel = QLabel("暂无")
        self.one_folder_checkbox = QCheckBox("单目录")
        
        comicIntroLabel = QLabel("简介: ")
        self.comicIntro = QLabel("暂无")
        self.comicIntro.setWordWrap(True)
 
        chapterGroupBox = QGroupBox("章节列表:")
        
        self.chapterListView = QListWidget(chapterGroupBox)
        self.chapterListView.setSelectionMode(QAbstractItemView.ExtendedSelection)
        self.chapterListView.setEnabled(False)
 
        groupBoxLayout = QHBoxLayout(chapterGroupBox)
        groupBoxLayout.addWidget(self.chapterListView)
 
        self.downloadButton = QPushButton("下载选中")
        self.statusLabel = QLabel("输入要下载的漫画的首页，然后点分析")
        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("腾讯漫画下载")
        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('下载选中')
            self.chapterListView.setFocus()
 
    def getPath(self):
        path = str(QFileDialog.getExistingDirectory(self, "选择下载目录"))
        if path:
            self.pathLine.setText(path)
 
    def anaysisURL(self):
        url = self.nameLine.text()
 
        self.downloadButton.setEnabled(False)
        self.comicNameLabel.setText("暂无")
        self.comicIntro.setText("暂无")
        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('选择要下载的章节后点击右侧按钮')
 
                for i in range(len(self.contentNameList)):
                    self.chapterListView.addItem('第{0:0>4}话-{1}'.format(i+1, self.contentNameList[i]))
                    self.chapterListView.item(i).setSelected(True)
 
                self.downloadButton.setEnabled(True)
 
            else:
                self.statusLabel.setText('<font color="red">错误的URL格式！请输入正确的漫画首页地址！</font>')
 
        except getComic.ErrorCode as e:
            if e.code == 2:
                self.statusLabel.setText('<font color="red">无法跳转为移动端URL,请进入http://m.ac.qq.com找到该漫画地址</font>')
 
        except KeyError:
            self.statusLabel.setText('<font color="red">不存在的地址</font>')
 
    def download(self):
        self.downloadButton.setText("下载中...")
        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) #将windows下的非法字符一律替换为_
        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 = '正在下载第{0:0>4}话: {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}话-{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('完毕!')
       
        except Exception as e:
            self.output.emit('<font color="red">{}</font>\n'
                    '遇到异常!请尝试重新点击下载按钮重试'.format(e))
            raise
 
        finally:
            self.finished.emit()
 
if __name__ == '__main__':
    app = QApplication(sys.argv)
 
    main = TencentComicDownloader()
    main.show()
 
    app.exec_()