def __getNextPage(self, imgUrl):
url = makeURL(
'https://' + self.domain + '.book118.com/PW/GetPage/?', {
'f': self.pdfInfo['Url'],
'img': imgUrl,
'isMobile': 'false',
'isNet': 'True',
'readLimit': self.pdfInfo['ReadLimit'],
'furl': self.pdfInfo['Furl']
})
result = ''
while True:
result = getHTML(url)
if (result.startswith('{') and result.endswith('}')):
break
else:
print(result, file=sys.stderr)
res = json.loads(result)
if self.total == 0:
self.total = res['PageCount']
self.index = res['PageIndex']
self.imgList.append(res['NextPage'])
print(self.index, '/', self.total, 'url finish', res['NextPage'])
return res
def __getPdfInfo(self):
url = makeURL(
'https://max.book118.com/index.php?', {
'g': 'Home',
'm': 'View',
'a': 'viewUrl',
'cid': str(self.pid),
'flag': '1'
})
viewPage = getHTML(url)
self.domain = re.findall(r'//(.*?)\..*', viewPage)[0]
rawHTML = getHTML('https:' + viewPage)
res = re.findall(r'<input type="hidden" id="(.*?)" value="(.*?)".*?/>',
rawHTML)
for lst in res:
self.pdfInfo[lst[0]] = lst[1]
def __getIMG(self):
if os.path.exists('./temp'):
shutil.rmtree('./temp')
os.makedirs('./temp')
for (idx, img) in enumerate(self.imgList):
res = getHTML(
makeURL('http://' + self.domain + '.book118.com/img/?', {'img': img}), byte=True)
with open('./temp/' + str(idx + 1) + '.jpg', 'wb') as f:
f.write(res)
print(idx + 1, '/', self.total,
'download finish', str(idx + 1) + '.jpg')
self.imgFileList.append('./temp/' + str(idx + 1) + '.jpg')
# ?img=Hs92T42xAvsP_ycWPqjcj8Iw69WUDaxvq4HtxAb3Zl3WYzxX1hdIsZzydhmmGAtm
pass
def __getNextPage(self, imgUrl):
url = makeURL(
'https://' + self.domain + '.book118.com/pdf/GetNextPage/?', {
'f': self.pdfInfo['Url'],
'img': imgUrl,
'isMobile': 'false',
'isNet': 'True',
'readLimit': self.pdfInfo['ReadLimit'],
'furl': self.pdfInfo['Furl']
})
result = getHTML(url)
res = json.loads(result)
if self.total == 0:
self.total = res['PageCount']
self.index = res['PageIndex']
self.imgList.append(res['NextPage'])
print(self.index, '/', self.total, 'url finish', res['NextPage'])
return res