def scanSingleDir(self, dirPath):
self.log.info("Dir %s", dirPath)
items = os.listdir(dirPath)
items.sort()
for item in items:
item = os.path.join(dirPath, item)
if os.path.isfile(item):
fPath, fName = os.path.split(item)
guessName = nt.guessSeriesFromFilename(fName)
dirName = fPath.strip("/").split("/")[-1]
guess2 = nt.guessSeriesFromFilename(dirName)
dist = lv.distance(guessName, guess2)
# Assumption: The filename probably has shit tacked onto it.
# Therefore, the allowable edit distance delta is the extent to
# which the filename is longer then the dirname
normed = dist - (len(guessName) - len(guess2))
if normed > 0:
self.log.warning("Wat: %s",
(normed, item, guessName, guess2))
elif normed < 0:
self.log.error("Wat: %s",
(normed, item, guessName, guess2))
else:
if guess2 in nt.dirNameProxy and nt.dirNameProxy[guess2][
"fqPath"]:
itemInfo = nt.dirNameProxy[guess2]
# print(itemInfo)
if itemInfo["fqPath"] != dirPath:
dstDir = itemInfo["fqPath"]
print("Move file '%s' from:" % fName)
print(" Src = '%s'" % fPath)
print(" Dst = '%s'" % dstDir)
dstPath = os.path.join(dstDir, fName)
try:
shutil.move(item, dstPath)
# Set pron to True, to prevent accidental uploading.
processDownload.processDownload(
guess2,
dstPath,
deleteDups=True,
includePHash=True,
pron=True,
crossReference=False)
except KeyboardInterrupt:
shutil.move(dstPath, item)
raise
else:
print("No match: ", fName)
def getLink(self, link):
sourceUrl = link["sourceUrl"]
seriesName = link["seriesName"]
originFileName = link["originName"]
self.updateDbEntry(sourceUrl, dlState=1)
self.log.info("Downloading = '%s', '%s'", seriesName, originFileName)
dlPath, newDir = self.locateOrCreateDirectoryForSeries(seriesName)
if link["flags"] == None:
link["flags"] = ""
if newDir:
self.updateDbEntry(sourceUrl, flags=" ".join([link["flags"], "haddir"]))
self.conn.commit()
try:
content, headerName = self.getLinkFile(sourceUrl)
except:
self.log.error("Unrecoverable error retreiving content %s", link)
self.log.error("Traceback: %s", traceback.format_exc())
self.updateDbEntry(sourceUrl, dlState=-1)
return
headerName = urllib.parse.unquote(headerName)
fName = "%s - %s" % (originFileName, headerName)
fName = nt.makeFilenameSafe(fName)
fName, ext = os.path.splitext(fName)
fName = "%s [CXC Scans]%s" % (fName, ext)
fqFName = os.path.join(dlPath, fName)
self.log.info("SaveName = %s", fqFName)
loop = 1
while os.path.exists(fqFName):
fName, ext = os.path.splitext(fName)
fName = "%s (%d)%s" % (fName, loop, ext)
fqFName = os.path.join(link["targetDir"], fName)
loop += 1
self.log.info("Writing file")
filePath, fileName = os.path.split(fqFName)
try:
with open(fqFName, "wb") as fp:
fp.write(content)
except TypeError:
self.log.error("Failure trying to retreive content from source %s", sourceUrl)
self.updateDbEntry(sourceUrl, dlState=-4, downloadPath=filePath, fileName=fileName)
return
# self.log.info( filePath)
dedupState = processDownload.processDownload(seriesName, fqFName, deleteDups=True)
self.log.info("Done")
self.updateDbEntry(sourceUrl, dlState=2, downloadPath=filePath, fileName=fileName, tags=dedupState)
return
def getLink(self, linkDict):
try:
linkDict = self.getDownloadInfo(linkDict)
images = self.getImages(linkDict)
title = linkDict['title']
artist = linkDict['artist']
except webFunctions.ContentError:
self.updateDbEntry(linkDict["sourceUrl"], dlState=-2, downloadPath="ERROR", fileName="ERROR: FAILED")
return False
if images and title:
fileN = title+" "+artist+".zip"
fileN = nt.makeFilenameSafe(fileN)
# self.log.info("geturl with processing", fileN)
wholePath = os.path.join(linkDict["dirPath"], fileN)
wholePath = self.insertCountIfFilenameExists(wholePath)
self.log.info("Complete filepath: %s", wholePath)
#Write all downloaded files to the archive.
try:
arch = zipfile.ZipFile(wholePath, "w")
except OSError:
title = title.encode('ascii','ignore').decode('ascii')
fileN = title+".zip"
fileN = nt.makeFilenameSafe(fileN)
wholePath = os.path.join(linkDict["dirPath"], fileN)
arch = zipfile.ZipFile(wholePath, "w")
for imageName, imageContent in images:
arch.writestr(imageName, imageContent)
arch.close()
self.log.info("Successfully Saved to path: %s", wholePath)
self.updateDbEntry(linkDict["sourceUrl"], downloadPath=linkDict["dirPath"], fileName=fileN)
# Deduper uses the path info for relinking, so we have to dedup the item after updating the downloadPath and fileN
dedupState = processDownload.processDownload(None, wholePath, pron=True, deleteDups=True, includePHash=True, rowId=linkDict['dbId'])
self.log.info( "Done")
if dedupState:
self.addTags(sourceUrl=linkDict["sourceUrl"], tags=dedupState)
self.updateDbEntry(linkDict["sourceUrl"], dlState=2)
return wholePath
else:
self.updateDbEntry(linkDict["sourceUrl"], dlState=-1, downloadPath="ERROR", fileName="ERROR: FAILED")
return False
def scanSingleDir(self, dirPath):
self.log.info("Dir %s", dirPath)
items = os.listdir(dirPath)
items.sort()
for item in items:
item = os.path.join(dirPath, item)
if os.path.isfile(item):
fPath, fName = os.path.split(item)
guessName = nt.guessSeriesFromFilename(fName)
dirName = fPath.strip("/").split("/")[-1]
guess2 = nt.guessSeriesFromFilename(dirName)
dist = lv.distance(guessName, guess2)
# Assumption: The filename probably has shit tacked onto it.
# Therefore, the allowable edit distance delta is the extent to
# which the filename is longer then the dirname
normed = dist - (len(guessName) - len(guess2))
if normed > 0:
self.log.warning("Wat: %s", (normed, item, guessName, guess2))
elif normed < 0:
self.log.error("Wat: %s", (normed, item, guessName, guess2))
else:
if guess2 in nt.dirNameProxy and nt.dirNameProxy[guess2]["fqPath"]:
itemInfo = nt.dirNameProxy[guess2]
# print(itemInfo)
if itemInfo["fqPath"] != dirPath:
dstDir = itemInfo["fqPath"]
print("Move file '%s' from:" % fName)
print(" Src = '%s'" % fPath)
print(" Dst = '%s'" % dstDir)
dstPath = os.path.join(dstDir, fName)
try:
shutil.move(item, dstPath)
# Set pron to True, to prevent accidental uploading.
processDownload.processDownload(guess2, dstPath, deleteDups=True, includePHash=True, pron=True, crossReference=False)
except KeyboardInterrupt:
shutil.move(dstPath, item)
raise
else:
print("No match: ", fName)
def getLink(self, link):
sourceUrl, originFileName = link["sourceUrl"], link["originName"]
self.log.info( "Should retreive: %s, url - %s", originFileName, sourceUrl)
self.updateDbEntry(sourceUrl, dlState=1)
self.conn.commit()
fileUrl = self.getDownloadUrl(sourceUrl)
if fileUrl is None:
self.log.warning("Could not find url!")
self.deleteRowsByValue(sourceUrl=sourceUrl)
return
try:
content, hName = self.getLinkFile(fileUrl, sourceUrl)
except:
self.log.error("Unrecoverable error retreiving content %s", link)
self.log.error("Traceback: %s", traceback.format_exc())
self.updateDbEntry(sourceUrl, dlState=-1)
return
# print("Content type = ", type(content))
# And fix %xx crap
hName = urllib.parse.unquote(hName)
fName = "%s - %s" % (originFileName, hName)
fName = nt.makeFilenameSafe(fName)
fqFName = os.path.join(link["targetDir"], fName)
self.log.info( "SaveName = %s", fqFName)
loop = 1
while os.path.exists(fqFName):
fName = "%s - (%d) - %s" % (originFileName, loop, hName)
fqFName = os.path.join(link["targetDir"], fName)
loop += 1
self.log.info( "Writing file")
filePath, fileName = os.path.split(fqFName)
try:
with open(fqFName, "wb") as fp:
fp.write(content)
except TypeError:
self.log.error("Failure trying to retreive content from source %s", sourceUrl)
return
#self.log.info( filePath)
dedupState = processDownload.processDownload(link["seriesName"], fqFName, deleteDups=True, includePHash=True)
self.log.info( "Done")
self.updateDbEntry(sourceUrl, dlState=2, downloadPath=filePath, fileName=fileName, tags=dedupState)
return
def doDownload(self, linkDict, retag=False):
downloadUrl = self.getDownloadUrl(linkDict["dlPage"], linkDict["sourceUrl"])
if downloadUrl:
fCont, fName = self.wg.getFileAndName(downloadUrl)
# self.log.info(len(content))
if linkDict["originName"] in fName:
fileN = fName
else:
fileN = "%s - %s.zip" % (linkDict["originName"], fName)
fileN = fileN.replace(".zip .zip", ".zip")
fileN = nt.makeFilenameSafe(fileN)
chop = len(fileN) - 4
wholePath = "ERROR"
while 1:
try:
fileN = fileN[:chop] + fileN[-4:]
# self.log.info("geturl with processing", fileN)
wholePath = os.path.join(linkDict["dirPath"], fileN)
self.log.info("Complete filepath: %s", wholePath)
# Write all downloaded files to the archive.
with open(wholePath, "wb") as fp:
fp.write(fCont)
self.log.info("Successfully Saved to path: %s", wholePath)
break
except IOError:
chop = chop - 1
self.log.warn("Truncating file length to %s characters.", chop)
if not linkDict["tags"]:
linkDict["tags"] = ""
self.updateDbEntry(linkDict["sourceUrl"], downloadPath=linkDict["dirPath"], fileName=fileN)
# Deduper uses the path info for relinking, so we have to dedup the item after updating the downloadPath and fileN
dedupState = processDownload.processDownload(linkDict["seriesName"], wholePath, pron=True)
self.log.info("Done")
if dedupState:
self.addTags(sourceUrl=linkDict["sourceUrl"], tags=dedupState)
self.updateDbEntry(linkDict["sourceUrl"], dlState=2)
self.conn.commit()
else:
self.updateDbEntry(linkDict["sourceUrl"], dlState=-1, downloadPath="ERROR", fileName="ERROR: FAILED")
self.conn.commit()
return False
def fetchLinkList(self, itemList):
dbInt = utilities.EmptyRetreivalDb.ScraperDbTool()
try:
for item in itemList:
srcStr = 'import-{hash}'.format(hash=hashlib.md5(item.encode("utf-8")).hexdigest())
itemtags = self.extractTags(item)
if itemtags == "None" or itemtags == None:
itemtags = ''
fPath = os.path.join(settings.djMoeDir, "imported")
if not os.path.exists(fPath):
os.makedirs(fPath)
srcPath = os.path.join(self.sourcePath, item)
dstPath = os.path.join(fPath, item)
if os.path.exists(dstPath):
raise ValueError("Destination path already exists? = '%s'" % dstPath)
# print("os.path.exists", os.path.exists(srcPath), os.path.exists(dstPath))
# print("Item '%s' '%s' '%s'" % (srcPath, dstPath, itemtags))
shutil.move(srcPath, dstPath)
dbInt.insertIntoDb(retreivalTime=200,
sourceUrl=srcStr,
originName=item,
dlState=2,
downloadPath=fPath,
fileName=item,
seriesName="imported")
dedupState = processDownload.processDownload("imported", dstPath, pron=True, deleteDups=True)
tags = dedupState + ' ' + ' '.join(itemtags)
tags = tags.strip()
if dedupState:
dbInt.addTags(sourceUrl=srcStr, tags=tags)
self.log.info( "Done")
if not runStatus.run:
self.log.info( "Breaking due to exit flag being set")
break
except:
self.log.critical("Exception!")
traceback.print_exc()
self.log.critical(traceback.format_exc())
def fetchLinkList(self, itemList):
dbInt = utilities.EmptyRetreivalDb.ScraperDbTool()
try:
for item in itemList:
srcStr = 'import-{hash}'.format(hash=hashlib.md5(item.encode("utf-8")).hexdigest())
itemtags = self.extractTags(item)
if itemtags == "None" or itemtags == None:
itemtags = ''
fPath = os.path.join(settings.djMoeDir, "imported")
if not os.path.exists(fPath):
os.makedirs(fPath)
srcPath = os.path.join(self.sourcePath, item)
dstPath = os.path.join(fPath, item)
if os.path.exists(dstPath):
raise ValueError("Destination path already exists? = '%s'" % dstPath)
# print("os.path.exists", os.path.exists(srcPath), os.path.exists(dstPath))
# print("Item '%s' '%s' '%s'" % (srcPath, dstPath, itemtags))
shutil.move(srcPath, dstPath)
dbInt.insertIntoDb(retreivalTime=200,
sourceUrl=srcStr,
originName=item,
dlState=2,
downloadPath=fPath,
fileName=item,
seriesName="imported")
dedupState = processDownload.processDownload("imported", dstPath, pron=True, deleteDups=True)
tags = dedupState + ' ' + ' '.join(itemtags)
tags = tags.strip()
if dedupState:
dbInt.addTags(sourceUrl=srcStr, tags=tags)
self.log.info( "Done")
if not runStatus.run:
self.log.info( "Breaking due to exit flag being set")
break
except:
self.log.critical("Exception!")
traceback.print_exc()
self.log.critical(traceback.format_exc())
def getFile(self, file_data):
row = self.getRowsByValue(sourceUrl=file_data["baseUrl"],
limitByKey=False)
if row and row[0]['dlState'] != 0:
return
if not row:
self.insertIntoDb(retreivalTime=time.time(),
sourceUrl=file_data["baseUrl"],
originName=file_data["title"],
dlState=1,
seriesName=file_data["title"])
image_links = self.getFileInfo(file_data)
images = []
for imagen, imageurl in image_links:
imdat = self.get_image(imageurl, file_data['xor_key'])
images.append((imagen, imdat))
# filen = nt.makeFilenameSafe(file_data['title'] + " - " + imagen)
# with open(filen, "wb") as fp:
# fp.write(imdat)
fileN = '{series} - c{chapNo:03.0f} [MangaBox].zip'.format(
series=file_data['title'], chapNo=file_data['chapter'])
fileN = nt.makeFilenameSafe(fileN)
dlPath, newDir = self.locateOrCreateDirectoryForSeries(
file_data["title"])
wholePath = os.path.join(dlPath, fileN)
if newDir:
self.updateDbEntry(file_data["baseUrl"], flags="haddir")
self.conn.commit()
arch = zipfile.ZipFile(wholePath, "w")
for imageName, imageContent in images:
arch.writestr(imageName, imageContent)
arch.close()
self.log.info("Successfully Saved to path: %s", wholePath)
dedupState = processDownload.processDownload(file_data["title"],
wholePath,
deleteDups=True)
if dedupState:
self.addTags(sourceUrl=file_data["baseUrl"], tags=dedupState)
self.updateDbEntry(file_data["baseUrl"],
dlState=2,
downloadPath=dlPath,
fileName=fileN,
originName=fileN)
self.conn.commit()
self.log.info("Done")
def doDownload(self, linkDict, retag=False):
images = self.fetchImages(linkDict)
# images = ['wat']
# print(linkDict)
# self.log.info(len(content))
if images:
linkDict["chapterNo"] = float(linkDict["chapterNo"])
fileN = '{series} - c{chapNo:06.1f} - {sourceName} [crunchyroll].zip'.format(
series=linkDict['seriesName'],
chapNo=linkDict["chapterNo"],
sourceName=linkDict['originName'])
fileN = nt.makeFilenameSafe(fileN)
# self.log.info("geturl with processing", fileN)
wholePath = os.path.join(linkDict["dirPath"], fileN)
self.log.info("Complete filepath: %s", wholePath)
#Write all downloaded files to the archive.
arch = zipfile.ZipFile(wholePath, "w")
for imageName, imageContent in images:
arch.writestr(imageName, imageContent)
arch.close()
self.log.info("Successfully Saved to path: %s", wholePath)
if not linkDict["tags"]:
linkDict["tags"] = ""
dedupState = processDownload.processDownload(
linkDict["seriesName"], wholePath, deleteDups=True)
self.log.info("Done")
if dedupState:
self.addTags(sourceUrl=linkDict["sourceUrl"], tags=dedupState)
self.updateDbEntry(linkDict["sourceUrl"],
dlState=2,
downloadPath=linkDict["dirPath"],
fileName=fileN,
originName=fileN)
self.conn.commit()
return wholePath
else:
self.updateDbEntry(linkDict["sourceUrl"],
dlState=-1,
downloadPath="ERROR",
fileName="ERROR: FAILED")
self.conn.commit()
return False
def doDownload(self, linkDict, retag=False):
images = self.fetchImages(linkDict)
# self.log.info(len(content))
if images:
fileN = linkDict['originName']+".zip"
fileN = nt.makeFilenameSafe(fileN)
# self.log.info("geturl with processing", fileN)
wholePath = os.path.join(linkDict["dirPath"], fileN)
self.log.info("Complete filepath: %s", wholePath)
#Write all downloaded files to the archive.
arch = zipfile.ZipFile(wholePath, "w")
for imageName, imageContent in images:
arch.writestr(imageName, imageContent)
arch.close()
self.log.info("Successfully Saved to path: %s", wholePath)
if not linkDict["tags"]:
linkDict["tags"] = ""
self.updateDbEntry(linkDict["sourceUrl"], downloadPath=linkDict["dirPath"], fileName=fileN)
# Deduper uses the path info for relinking, so we have to dedup the item after updating the downloadPath and fileN
dedupState = processDownload.processDownload(None, wholePath, pron=True, deleteDups=True, includePHash=True)
self.log.info( "Done")
if dedupState:
self.addTags(sourceUrl=linkDict["sourceUrl"], tags=dedupState)
self.updateDbEntry(linkDict["sourceUrl"], dlState=2)
self.conn.commit()
return wholePath
else:
self.updateDbEntry(linkDict["sourceUrl"], dlState=-1, downloadPath="ERROR", fileName="ERROR: FAILED")
self.conn.commit()
return False
def getFile(self, file_data):
row = self.getRowsByValue(sourceUrl=file_data["baseUrl"], limitByKey=False)
if row and row[0]['dlState'] != 0:
return
if not row:
self.insertIntoDb(retreivalTime = time.time(),
sourceUrl = file_data["baseUrl"],
originName = file_data["title"],
dlState = 1,
seriesName = file_data["title"])
image_links = self.getFileInfo(file_data)
images = []
for imagen, imageurl in image_links:
imdat = self.get_image(imageurl, file_data['xor_key'])
images.append((imagen, imdat))
# filen = nt.makeFilenameSafe(file_data['title'] + " - " + imagen)
# with open(filen, "wb") as fp:
# fp.write(imdat)
fileN = '{series} - c{chapNo:03.0f} [MangaBox].zip'.format(series=file_data['title'], chapNo=file_data['chapter'])
fileN = nt.makeFilenameSafe(fileN)
dlPath, newDir = self.locateOrCreateDirectoryForSeries(file_data["title"])
wholePath = os.path.join(dlPath, fileN)
if newDir:
self.updateDbEntry(file_data["baseUrl"], flags="haddir")
self.conn.commit()
arch = zipfile.ZipFile(wholePath, "w")
for imageName, imageContent in images:
arch.writestr(imageName, imageContent)
arch.close()
self.log.info("Successfully Saved to path: %s", wholePath)
dedupState = processDownload.processDownload(file_data["title"], wholePath, deleteDups=True)
if dedupState:
self.addTags(sourceUrl=file_data["baseUrl"], tags=dedupState)
self.updateDbEntry(file_data["baseUrl"], dlState=2, downloadPath=dlPath, fileName=fileN, originName=fileN)
self.conn.commit()
self.log.info( "Done")
def xdcc_receive_finish(self):
self.log.info("XDCC Transfer starting!")
self.changeState("xdcc finished")
dedupState = processDownload.processDownload(self.currentItem["seriesName"], self.currentItem["downloadPath"], deleteDups=True)
self.log.info( "Done")
self.db.addTags(dbId=self.currentItem["dbId"], tags=dedupState)
if dedupState != "damaged":
self.db.updateDbEntry(self.currentItem["sourceUrl"], dlState=2)
else:
self.db.updateDbEntry(self.currentItem["sourceUrl"], dlState=-10)
def doDownload(self, linkDict, retag=False):
images = self.fetchImages(linkDict)
# images = ['wat']
# print(linkDict)
# self.log.info(len(content))
if images:
linkDict["chapterNo"] = float(linkDict["chapterNo"])
fileN = '{series} - c{chapNo:06.1f} - {sourceName} [crunchyroll].zip'.format(series=linkDict['seriesName'], chapNo=linkDict["chapterNo"], sourceName=linkDict['originName'])
fileN = nt.makeFilenameSafe(fileN)
# self.log.info("geturl with processing", fileN)
wholePath = os.path.join(linkDict["dirPath"], fileN)
self.log.info("Complete filepath: %s", wholePath)
#Write all downloaded files to the archive.
arch = zipfile.ZipFile(wholePath, "w")
for imageName, imageContent in images:
arch.writestr(imageName, imageContent)
arch.close()
self.log.info("Successfully Saved to path: %s", wholePath)
if not linkDict["tags"]:
linkDict["tags"] = ""
dedupState = processDownload.processDownload(linkDict["seriesName"], wholePath, deleteDups=True)
self.log.info( "Done")
if dedupState:
self.addTags(sourceUrl=linkDict["sourceUrl"], tags=dedupState)
self.updateDbEntry(linkDict["sourceUrl"], dlState=2, downloadPath=linkDict["dirPath"], fileName=fileN, originName=fileN)
self.conn.commit()
return wholePath
else:
self.updateDbEntry(linkDict["sourceUrl"], dlState=-1, downloadPath="ERROR", fileName="ERROR: FAILED")
self.conn.commit()
return False
def doDownload(self, seriesName, dlurl, chapter_name):
row = self.getRowsByValue(sourceUrl=dlurl, limitByKey=False)
if row and row[0]['dlState'] != 0:
return
if not row:
self.insertIntoDb(retreivalTime=time.time(),
sourceUrl=dlurl,
originName=seriesName,
dlState=1,
seriesName=seriesName)
fctnt, fname = self.wg.getFileAndName(dlurl)
fileN = '{series} - {chap} [YoManga].zip'.format(series=seriesName,
chap=chapter_name)
fileN = nt.makeFilenameSafe(fileN)
dlPath, newDir = self.locateOrCreateDirectoryForSeries(seriesName)
wholePath = os.path.join(dlPath, fileN)
self.log.info("Source name: %s", fname)
self.log.info("Generated name: %s", fileN)
if newDir:
self.updateDbEntry(dlurl, flags="haddir")
self.conn.commit()
with open(wholePath, "wb") as fp:
fp.write(fctnt)
self.log.info("Successfully Saved to path: %s", wholePath)
dedupState = processDownload.processDownload(seriesName,
wholePath,
deleteDups=True)
if dedupState:
self.addTags(sourceUrl=dlurl, tags=dedupState)
self.updateDbEntry(dlurl,
dlState=2,
downloadPath=dlPath,
fileName=fileN,
originName=fileN)
self.conn.commit()
def doDownload(self, seriesName, dlurl, chapter_name):
row = self.getRowsByValue(sourceUrl=dlurl, limitByKey=False)
if row and row[0]['dlState'] != 0:
return
if not row:
self.insertIntoDb(retreivalTime = time.time(),
sourceUrl = dlurl,
originName = seriesName,
dlState = 1,
seriesName = seriesName)
fctnt, fname = self.wg.getFileAndName(dlurl)
fileN = '{series} - {chap} [YoManga].zip'.format(series=seriesName, chap=chapter_name)
fileN = nt.makeFilenameSafe(fileN)
dlPath, newDir = self.locateOrCreateDirectoryForSeries(seriesName)
wholePath = os.path.join(dlPath, fileN)
self.log.info("Source name: %s", fname)
self.log.info("Generated name: %s", fileN)
if newDir:
self.updateDbEntry(dlurl, flags="haddir")
self.conn.commit()
with open(wholePath, "wb") as fp:
fp.write(fctnt)
self.log.info("Successfully Saved to path: %s", wholePath)
dedupState = processDownload.processDownload(seriesName, wholePath, deleteDups=True)
if dedupState:
self.addTags(sourceUrl=dlurl, tags=dedupState)
self.updateDbEntry(dlurl, dlState=2, downloadPath=dlPath, fileName=fileN, originName=fileN)
self.conn.commit()
def getLink(self, link):
sourceUrl = link["sourceUrl"]
seriesName = link["seriesName"]
chapterVol = link["originName"]
try:
self.log.info( "Should retreive url - %s", sourceUrl)
self.updateDbEntry(sourceUrl, dlState=1)
imageUrls = self.getImageUrls(sourceUrl)
if not imageUrls:
self.log.critical("Failure on retreiving content at %s", sourceUrl)
self.log.critical("Page not found - 404")
self.updateDbEntry(sourceUrl, dlState=-1)
return
self.log.info("Downloading = '%s', '%s'", seriesName, chapterVol)
dlPath, newDir = self.locateOrCreateDirectoryForSeries(seriesName)
if link["flags"] == None:
link["flags"] = ""
if newDir:
self.updateDbEntry(sourceUrl, flags=" ".join([link["flags"], "haddir"]))
self.conn.commit()
chapterName = nt.makeFilenameSafe(chapterVol)
fqFName = os.path.join(dlPath, chapterName+"[MangaCow].zip")
loop = 1
while os.path.exists(fqFName):
fqFName, ext = os.path.splitext(fqFName)
fqFName = "%s (%d)%s" % (fqFName, loop, ext)
loop += 1
self.log.info("Saving to archive = %s", fqFName)
images = []
for imgUrl, referrerUrl in imageUrls:
imageName, imageContent = self.getImage(imgUrl, referrerUrl)
images.append([imageName, imageContent])
if not runStatus.run:
self.log.info( "Breaking due to exit flag being set")
self.updateDbEntry(sourceUrl, dlState=0)
return
self.log.info("Creating archive with %s images", len(images))
if not images:
self.updateDbEntry(sourceUrl, dlState=-1, seriesName=seriesName, originName=chapterVol, tags="error-404")
return
#Write all downloaded files to the archive.
arch = zipfile.ZipFile(fqFName, "w")
for imageName, imageContent in images:
arch.writestr(imageName, imageContent)
arch.close()
dedupState = processDownload.processDownload(seriesName, fqFName, deleteDups=True, includePHash=True, phashThresh=6)
self.log.info( "Done")
filePath, fileName = os.path.split(fqFName)
self.updateDbEntry(sourceUrl, dlState=2, downloadPath=filePath, fileName=fileName, seriesName=seriesName, originName=chapterVol, tags=dedupState)
return
except Exception:
self.log.critical("Failure on retreiving content at %s", sourceUrl)
self.log.critical("Traceback = %s", traceback.format_exc())
self.updateDbEntry(sourceUrl, dlState=-1)
def doDownload(self, linkDict, link, retag=False):
downloadUrl = self.getDownloadUrl(linkDict['dlPage'],
linkDict["sourceUrl"])
if downloadUrl:
fCont, fName = self.wg.getFileAndName(downloadUrl)
# self.log.info(len(content))
if linkDict['originName'] in fName:
fileN = fName
else:
fileN = '%s - %s.zip' % (linkDict['originName'], fName)
fileN = fileN.replace('.zip .zip', '.zip')
fileN = nt.makeFilenameSafe(fileN)
chop = len(fileN) - 4
wholePath = "ERROR"
while 1:
try:
fileN = fileN[:chop] + fileN[-4:]
# self.log.info("geturl with processing", fileN)
wholePath = os.path.join(linkDict["dirPath"], fileN)
wholePath = self.insertCountIfFilenameExists(wholePath)
self.log.info("Complete filepath: %s", wholePath)
#Write all downloaded files to the archive.
with open(wholePath, "wb") as fp:
fp.write(fCont)
fileN = os.path.split(wholePath)[-1]
self.log.info("Succesfully Saved to path: %s", wholePath)
break
except IOError:
chop = chop - 1
self.log.warn("Truncating file length to %s characters.",
chop)
if not linkDict["tags"]:
linkDict["tags"] = ""
self.updateDbEntry(linkDict["sourceUrl"],
downloadPath=linkDict["dirPath"],
fileName=fileN)
# Deduper uses the path info for relinking, so we have to dedup the item after updating the downloadPath and fileN
dedupState = processDownload.processDownload(
linkDict["seriesName"],
wholePath,
pron=True,
rowId=link['dbId'])
self.log.info("Done")
if dedupState:
self.addTags(sourceUrl=linkDict["sourceUrl"], tags=dedupState)
self.updateDbEntry(linkDict["sourceUrl"], dlState=2)
else:
self.updateDbEntry(linkDict["sourceUrl"],
dlState=-1,
downloadPath="ERROR",
fileName="ERROR: FAILED")
return False
def doDownload(self, linkDict, retag=False):
images = self.fetchImages(linkDict)
# self.log.info(len(content))
if images:
fileN = linkDict['originName']+".zip"
fileN = nt.makeFilenameSafe(fileN)
# self.log.info("geturl with processing", fileN)
wholePath = os.path.join(linkDict["dirPath"], fileN)
self.log.info("Complete filepath: %s", wholePath)
#Write all downloaded files to the archive.
chop = len(fileN)-4
wholePath = "ERROR"
while 1:
try:
fileN = fileN[:chop]+fileN[-4:]
# self.log.info("geturl with processing", fileN)
wholePath = os.path.join(linkDict["dirPath"], fileN)
self.log.info("Complete filepath: %s", wholePath)
#Write all downloaded files to the archive.
arch = zipfile.ZipFile(wholePath, "w")
for imageName, imageContent in images:
arch.writestr(imageName, imageContent)
arch.close()
self.log.info("Successfully Saved to path: %s", wholePath)
break
except IOError:
chop = chop - 1
self.log.warn("Truncating file length to %s characters.", chop)
if not linkDict["tags"]:
linkDict["tags"] = ""
self.updateDbEntry(linkDict["sourceUrl"], downloadPath=linkDict["dirPath"], fileName=fileN)
# Deduper uses the path info for relinking, so we have to dedup the item after updating the downloadPath and fileN
dedupState = processDownload.processDownload(linkDict["seriesName"], wholePath, pron=True)
self.log.info( "Done")
if dedupState:
self.addTags(sourceUrl=linkDict["sourceUrl"], tags=dedupState)
self.updateDbEntry(linkDict["sourceUrl"], dlState=2)
self.conn.commit()
return wholePath
else:
self.updateDbEntry(linkDict["sourceUrl"], dlState=-1, downloadPath="ERROR", fileName="ERROR: FAILED")
self.conn.commit()
return False
def getLink(self, link):
sourceUrl = link["sourceUrl"]
print("Link", link)
try:
self.log.info( "Should retreive url - %s", sourceUrl)
# self.updateDbEntry(sourceUrl, dlState=1)
imageUrls, meta = self.getImageUrlsInfo(sourceUrl)
self.updateDbEntry(sourceUrl, seriesName=meta['series_name'])
seriesName = meta['series_name']
link["originName"] = meta['rel_name']
if not imageUrls:
self.log.critical("Failure on retreiving content at %s", sourceUrl)
self.log.critical("Page not found - 404")
# self.updateDbEntry(sourceUrl, dlState=-1)
return
self.log.info("Downloading = '%s', '%s' ('%s images)", seriesName, link["originName"], len(imageUrls))
dlPath, newDir = self.locateOrCreateDirectoryForSeries(seriesName)
if link["flags"] == None:
link["flags"] = ""
if newDir:
# self.updateDbEntry(sourceUrl, flags=" ".join([link["flags"], "haddir"]))
self.conn.commit()
chapterName = nt.makeFilenameSafe(link["originName"])
fqFName = os.path.join(dlPath, chapterName+" [Comic Zenon].zip")
loop = 1
prefix, ext = os.path.splitext(fqFName)
while os.path.exists(fqFName):
fqFName = "%s (%d)%s" % (prefix, loop, ext)
loop += 1
self.log.info("Saving to archive = %s", fqFName)
images = []
imgCnt = 1
for imgUrl in imageUrls:
imageName, imageContent = self.getImage(imgUrl, sourceUrl)
imageName = "{num:03.0f} - {srcName}".format(num=imgCnt, srcName=imageName)
imgCnt += 1
images.append([imageName, imageContent])
if not runStatus.run:
self.log.info( "Breaking due to exit flag being set")
# self.updateDbEntry(sourceUrl, dlState=0)
return
self.log.info("Creating archive with %s images", len(images))
if not images:
# self.updateDbEntry(sourceUrl, dlState=-1, tags="error-404")
return
#Write all downloaded files to the archive.
arch = zipfile.ZipFile(fqFName, "w")
for imageName, imageContent in images:
arch.writestr(imageName, imageContent)
arch.close()
dedupState = processDownload.processDownload(seriesName, fqFName, deleteDups=True, includePHash=True)
self.log.info( "Done")
filePath, fileName = os.path.split(fqFName)
# self.updateDbEntry(sourceUrl, dlState=2, downloadPath=filePath, fileName=fileName, tags=dedupState)
return
except Exception:
self.log.critical("Failure on retreiving content at %s", sourceUrl)
self.log.critical("Traceback = %s", traceback.format_exc())
# self.updateDbEntry(sourceUrl, dlState=-1)
raise
def getLink(self, link):
sourceUrl = link["sourceUrl"]
try:
self.log.info("Should retreive url - %s", sourceUrl)
self.updateDbEntry(sourceUrl, dlState=1)
seriesName, chapterVol, imageUrls = self.getContainerPages(
sourceUrl)
if not seriesName and not chapterVol and not imageUrls:
self.log.critical("Failure on retreiving content at %s",
sourceUrl)
self.log.critical("Page not found - 404")
self.updateDbEntry(sourceUrl, dlState=-1)
return
self.log.info("Downloading = '%s', '%s'", seriesName, chapterVol)
dlPath, newDir = self.locateOrCreateDirectoryForSeries(seriesName)
if link["flags"] == None:
link["flags"] = ""
if newDir:
self.updateDbEntry(sourceUrl,
flags=" ".join([link["flags"], "haddir"]))
chapterNameRaw = " - ".join((seriesName, chapterVol))
chapterName = nt.makeFilenameSafe(chapterNameRaw)
fqFName = os.path.join(dlPath, chapterName + " [batoto].zip")
loop = 1
while os.path.exists(fqFName):
fName = "%s [batoto] - (%d).zip" % (chapterName, loop)
fqFName = os.path.join(dlPath, fName)
loop += 1
self.log.info("Saving to archive = %s", fqFName)
images = []
for imgUrl in imageUrls:
self.log.info("Fetching content for item: %s", imgUrl)
imageName, imageContent = self.getImage(
imgUrl, "http://bato.to/reader")
images.append([imageName, imageContent])
if not runStatus.run:
self.log.info("Breaking due to exit flag being set")
self.updateDbEntry(sourceUrl, dlState=0)
return
self.log.info("Creating archive with %s images", len(images))
if not images:
self.updateDbEntry(sourceUrl,
dlState=-1,
seriesName=seriesName,
originName=chapterNameRaw,
tags="error-404")
return
#Write all downloaded files to the archive.
arch = zipfile.ZipFile(fqFName, "w")
for imageName, imageContent in images:
arch.writestr(imageName, imageContent)
arch.close()
dedupState = processDownload.processDownload(seriesName,
fqFName,
deleteDups=True,
includePHash=False,
rowId=link['dbId'])
self.log.info("Done")
filePath, fileName = os.path.split(fqFName)
self.updateDbEntry(sourceUrl,
dlState=2,
downloadPath=filePath,
fileName=fileName,
seriesName=seriesName,
originName=chapterNameRaw,
tags=dedupState)
return
except Exception:
self.log.critical("Failure on retreiving content at %s", sourceUrl)
self.log.critical("Traceback = %s", traceback.format_exc())
self.updateDbEntry(sourceUrl, dlState=-1)
def doDownload(self, linkDict):
images = []
containerUrl = linkDict["sourceUrl"] + "/read"
if "http://www.fakku.net/videos/" in containerUrl:
self.log.warning("Cannot download video items.")
self.updateDbEntry(linkDict["sourceUrl"],
dlState=-5,
downloadPath="Video",
fileName="ERROR: Video",
lastUpdate=time.time())
return False
if "http://www.fakku.net/games/" in containerUrl:
self.log.warning("Cannot download game items.")
self.updateDbEntry(linkDict["sourceUrl"],
dlState=-6,
downloadPath="Game",
fileName="ERROR: Game",
lastUpdate=time.time())
return False
try:
imagePage = self.wg.getpage(
containerUrl, addlHeaders={'Referer': linkDict["sourceUrl"]})
except urllib.error.URLError:
self.log.warning("Failure to retreive base page!.")
self.updateDbEntry(linkDict["sourceUrl"],
dlState=-1,
downloadPath="ERROR",
fileName="ERROR",
lastUpdate=time.time())
return False
if "This content has been disabled due to a DMCA takedown notice, it is no longer available to download or read online in your region." in imagePage:
self.log.warning(
"Assholes have DMCAed this item. Not available anymore.")
self.updateDbEntry(linkDict["sourceUrl"],
dlState=-4,
downloadPath="DMCA",
fileName="ERROR: DMCAed",
lastUpdate=time.time())
return False
if "Content does not exist." in imagePage:
self.log.warning("Page removed?.")
self.updateDbEntry(linkDict["sourceUrl"],
dlState=-7,
downloadPath="REMOVED",
fileName="ERROR: File removed",
lastUpdate=time.time())
return False
# F**k you Fakku, don't include pay-content in your free gallery system.
if "You must purchase this book in order to read it." in imagePage:
self.log.warning("Page removed?.")
self.updateDbEntry(linkDict["sourceUrl"],
dlState=-7,
downloadPath="REMOVED",
fileName="ERROR: Paywalled. ",
lastUpdate=time.time())
return False
# So...... Fakku's reader is completely javascript driven. No (easily) parseable shit here.
# Therefore: WE DECEND TO THE LEVEL OF REGEXBOMINATIONS!
pathFormatterRe = re.compile(
r"return '(//t\.fakku\.net/images/.+/.+/.+?/images/)' \+ x \+ '(\.jpg|\.gif|\.png)';",
re.IGNORECASE)
# We need to know how many images there are, but there is no convenient way to access this information.
# The fakku code internally uses the length of the thumbnail array for the number of images, so
# we extract that array, parse it (since it's javascript, variables are JSON, after all), and
# just look at the length ourselves as well.
thumbsListRe = re.compile(r"window\.params\.thumbs = (\[.+?\]);",
re.IGNORECASE)
thumbs = thumbsListRe.search(imagePage)
pathFormatter = pathFormatterRe.search(imagePage)
if not thumbs:
self.log.error("Could not find thumbnail array on page!")
self.log.error("URL: '%s'", containerUrl)
if not pathFormatter:
self.log.error("Could not find pathformatter on page!")
self.log.error("URL: '%s'", containerUrl)
items = json.loads(thumbs.group(1))
prefix, postfix = pathFormatter.group(1), pathFormatter.group(2)
print("pathFormatter = ", prefix, prefix)
imageUrls = []
for x in range(len(items)):
item = '{prefix}{num:03d}{postfix}'.format(
prefix=pathFormatter.group(1),
num=x + 1,
postfix=pathFormatter.group(2))
imageUrls.append(item)
# print("Prepared image URLs = ")
# print(imageUrls)
# print(linkDict)
images = []
try:
for imageUrl in imageUrls:
imagePath = urllib.parse.urlsplit(imageUrl)[2]
imageFileName = imagePath.split("/")[-1]
if imageUrl.startswith("//"):
imageUrl = "https:" + imageUrl
imageData = self.wg.getpage(
imageUrl, addlHeaders={'Referer': containerUrl})
images.append((imageFileName, imageData))
# Find next page
except urllib.error.URLError:
self.log.error("Failure retreiving item images.")
self.updateDbEntry(linkDict["sourceUrl"],
dlState=-1,
downloadPath="ERROR",
fileName="ERROR: Could not retreive images!",
lastUpdate=time.time())
self.conn.commit()
return False
# self.log.info(len(content))
if images:
fileN = linkDict["originName"] + ".zip"
fileN = nt.makeFilenameSafe(fileN)
# self.log.info("geturl with processing", fileN)
wholePath = os.path.join(linkDict["dirPath"], fileN)
self.log.info("Complete filepath: %s", wholePath)
#Write all downloaded files to the archive.
arch = zipfile.ZipFile(wholePath, "w")
for imageName, imageContent in images:
arch.writestr(imageName, imageContent)
arch.close()
self.log.info("Successfully Saved to path: %s", wholePath)
if not linkDict["tags"]:
linkDict["tags"] = ""
self.updateDbEntry(linkDict["sourceUrl"],
downloadPath=linkDict["dirPath"],
fileName=fileN)
# Deduper uses the path info for relinking, so we have to dedup the item after updating the downloadPath and fileN
dedupState = processDownload.processDownload(None,
wholePath,
pron=True,
deleteDups=True,
includePHash=True)
self.log.info("Done")
if dedupState:
self.addTags(sourceUrl=linkDict["sourceUrl"], tags=dedupState)
self.updateDbEntry(linkDict["sourceUrl"], dlState=2)
self.conn.commit()
return wholePath
else:
self.updateDbEntry(linkDict["sourceUrl"],
dlState=-1,
downloadPath="ERROR",
fileName="ERROR: FAILED",
lastUpdate=time.time())
self.conn.commit()
return False
def doDownload(self, linkDict):
images = []
title = None
nextPage = linkDict["dlLink"]
while nextPage:
gatewayPage = self.wg.getpage(
nextPage, addlHeaders={'Referer': linkDict["sourceUrl"]})
soup = bs4.BeautifulSoup(gatewayPage, "lxml")
titleCont = soup.find("div", class_="image-menu")
title = titleCont.h1.get_text()
title = title.replace("Reading ", "")
title, dummy = title.rsplit(" Page ", 1)
title = title.strip()
imageUrl = soup.find("img", class_="b")
imageUrl = urllib.parse.urljoin(self.urlBase, imageUrl["src"])
imagePath = urllib.parse.urlsplit(imageUrl)[2]
imageFileName = imagePath.split("/")[-1]
imageData = self.wg.getpage(imageUrl,
addlHeaders={'Referer': nextPage})
images.append((imageFileName, imageData))
# Find next page
nextPageLink = soup.find("a", class_="link-next")
if not nextPageLink:
nextPage = None
elif nextPageLink["href"].startswith(
"/finish/"): # Break on the last image.
nextPage = None
else:
nextPage = urllib.parse.urljoin(self.urlBase,
nextPageLink["href"])
# self.log.info(len(content))
if images and title:
fileN = title + ".zip"
fileN = nt.makeFilenameSafe(fileN)
# self.log.info("geturl with processing", fileN)
wholePath = os.path.join(linkDict["dirPath"], fileN)
self.log.info("Complete filepath: %s", wholePath)
#Write all downloaded files to the archive.
try:
arch = zipfile.ZipFile(wholePath, "w")
except OSError:
title = title.encode('ascii', 'ignore').decode('ascii')
fileN = title + ".zip"
fileN = nt.makeFilenameSafe(fileN)
wholePath = os.path.join(linkDict["dirPath"], fileN)
arch = zipfile.ZipFile(wholePath, "w")
for imageName, imageContent in images:
arch.writestr(imageName, imageContent)
arch.close()
self.log.info("Successfully Saved to path: %s", wholePath)
self.updateDbEntry(linkDict["sourceUrl"],
downloadPath=linkDict["dirPath"],
fileName=fileN)
# Deduper uses the path info for relinking, so we have to dedup the item after updating the downloadPath and fileN
dedupState = processDownload.processDownload(None,
wholePath,
pron=True,
deleteDups=True,
includePHash=True)
self.log.info("Done")
if dedupState:
self.addTags(sourceUrl=linkDict["sourceUrl"], tags=dedupState)
self.updateDbEntry(linkDict["sourceUrl"], dlState=2)
self.conn.commit()
return wholePath
else:
self.updateDbEntry(linkDict["sourceUrl"],
dlState=-1,
downloadPath="ERROR",
fileName="ERROR: FAILED")
self.conn.commit()
return False
def getLink(self, link):
sourceUrl = link["sourceUrl"]
print("Link", link)
seriesName = link['seriesName']
try:
self.log.info( "Should retreive url - %s", sourceUrl)
self.updateDbEntry(sourceUrl, dlState=1)
seriesName = nt.getCanonicalMangaUpdatesName(seriesName)
self.log.info("Downloading = '%s', '%s'", seriesName, link["originName"])
dlPath, newDir = self.locateOrCreateDirectoryForSeries(seriesName)
if link["flags"] == None:
link["flags"] = ""
if newDir:
self.updateDbEntry(sourceUrl, flags=" ".join([link["flags"], "haddir"]))
self.conn.commit()
chapterName = nt.makeFilenameSafe(link["originName"])
fqFName = os.path.join(dlPath, chapterName+" [MangaHere].zip")
loop = 1
prefix, ext = os.path.splitext(fqFName)
while os.path.exists(fqFName):
fqFName = "%s (%d)%s" % (prefix, loop, ext)
loop += 1
self.log.info("Saving to archive = %s", fqFName)
images = self.proceduralGetImages(sourceUrl)
self.log.info("Creating archive with %s images", len(images))
if not images:
self.updateDbEntry(sourceUrl, dlState=-1, tags="error-404")
return
#Write all downloaded files to the archive.
arch = zipfile.ZipFile(fqFName, "w")
for imageName, imageContent in images:
arch.writestr(imageName, imageContent)
arch.close()
dedupState = processDownload.processDownload(seriesName, fqFName, deleteDups=True, includePHash=True)
self.log.info( "Done")
filePath, fileName = os.path.split(fqFName)
self.updateDbEntry(sourceUrl, dlState=2, downloadPath=filePath, fileName=fileName, tags=dedupState)
return
except Exception:
self.log.critical("Failure on retreiving content at %s", sourceUrl)
self.log.critical("Traceback = %s", traceback.format_exc())
self.updateDbEntry(sourceUrl, dlState=-1)
raise
def getLink(self, link):
seriesName = link["seriesName"]
seriesName = seriesName.replace("[", "(").replace("]", "(")
safeBaseName = nt.makeFilenameSafe(link["seriesName"])
if seriesName in nt.dirNameProxy:
self.log.info( "Have target dir for '%s' Dir = '%s'", seriesName, nt.dirNameProxy[seriesName]['fqPath'])
link["targetDir"] = nt.dirNameProxy[seriesName]["fqPath"]
else:
self.log.info( "Don't have target dir for: %s Using default for: %s, full name = %s", seriesName, link["seriesName"], link["originName"])
targetDir = os.path.join(settings.mkSettings["dirs"]['mDlDir'], safeBaseName)
if not os.path.exists(targetDir):
try:
os.makedirs(targetDir)
link["targetDir"] = targetDir
self.updateDbEntry(link["sourceUrl"],flags=" ".join([link["flags"], "newdir"]))
self.conn.commit()
self.conn.commit()
except OSError:
self.log.critical("Directory creation failed?")
self.log.critical(traceback.format_exc())
else:
self.log.warning("Directory not found in dir-dict, but it exists!")
self.log.warning("Directory-Path: %s", targetDir)
link["targetDir"] = targetDir
self.updateDbEntry(link["sourceUrl"],flags=" ".join([link["flags"], "haddir"]))
self.conn.commit()
sourceUrl, originFileName = link["sourceUrl"], link["originName"]
self.log.info( "Should retreive: %s, url - %s", originFileName, sourceUrl)
self.updateDbEntry(sourceUrl, dlState=1)
self.conn.commit()
try:
content, hName = self.getLinkFile(sourceUrl)
except:
self.log.error("Unrecoverable error retreiving content %s", link)
self.log.error("Traceback: %s", traceback.format_exc())
self.updateDbEntry(sourceUrl, dlState=-1)
return
# print("Content type = ", type(content))
# And fix %xx crap
hName = urllib.parse.unquote(hName)
fName = "%s - %s" % (originFileName, hName)
fName = nt.makeFilenameSafe(fName)
fqFName = os.path.join(link["targetDir"], fName)
self.log.info( "SaveName = %s", fqFName)
loop = 1
while os.path.exists(fqFName):
fName = "%s - (%d) - %s" % (originFileName, loop, hName)
fqFName = os.path.join(link["targetDir"], fName)
loop += 1
self.log.info( "Writing file")
filePath, fileName = os.path.split(fqFName)
try:
chop = len(fileName)-4
wholePath = "ERROR"
while 1:
try:
fileName = fileName[:chop]+fileName[-4:]
# self.log.info("geturl with processing", fileName)
wholePath = os.path.join(filePath, fileName)
self.log.info("Complete filepath: %s", wholePath)
#Write all downloaded files to the archive.
with open(wholePath, "wb") as fp:
fp.write(content)
self.log.info("Successfully Saved to path: %s", wholePath)
break
except IOError:
chop = chop - 1
if chop < 200:
raise RuntimeError("Don't know what's going on, but a file truncated too far!")
self.log.warn("Truncating file length to %s characters.", chop)
except TypeError:
self.log.error("Failure trying to retreive content from source %s", sourceUrl)
self.updateDbEntry(sourceUrl, dlState=-4, downloadPath=filePath, fileName=fileName)
return
#self.log.info( filePath)
ext = os.path.splitext(fileName)[-1]
imageExts = ["jpg", "png", "bmp"]
if not any([ext.endswith(ex) for ex in imageExts]):
# We don't want to upload the file we just downloaded, so specify doUpload as false.
dedupState = processDownload.processDownload(False, fqFName, deleteDups=True, doUpload=False)
else:
dedupState = ""
self.log.info( "Done")
self.updateDbEntry(sourceUrl, dlState=2, downloadPath=filePath, fileName=fileName, tags=dedupState)
return
def getLink(self, link):
sourceUrl = link["sourceUrl"]
print("Link", link)
seriesName = link['seriesName']
try:
self.log.info("Should retreive url - %s", sourceUrl)
self.updateDbEntry(sourceUrl, dlState=1)
imageUrls = self.getImageUrls(sourceUrl)
if not imageUrls:
self.log.critical("Failure on retreiving content at %s",
sourceUrl)
self.log.critical("Page not found - 404")
self.updateDbEntry(sourceUrl, dlState=-1)
return
self.log.info("Downloading = '%s', '%s' ('%s images)", seriesName,
link["originName"], len(imageUrls))
dlPath, newDir = self.locateOrCreateDirectoryForSeries(seriesName)
if link["flags"] == None:
link["flags"] = ""
if newDir:
self.updateDbEntry(sourceUrl,
flags=" ".join([link["flags"], "haddir"]))
chapterName = nt.makeFilenameSafe(link["originName"])
fqFName = os.path.join(dlPath, chapterName + " [KissManga].zip")
loop = 1
prefix, ext = os.path.splitext(fqFName)
while os.path.exists(fqFName):
fqFName = "%s (%d)%s" % (prefix, loop, ext)
loop += 1
self.log.info("Saving to archive = %s", fqFName)
images = []
imgCnt = 1
for imgUrl in imageUrls:
imageName, imageContent = self.getImage(imgUrl, sourceUrl)
imageName = "{num:03.0f} - {srcName}".format(num=imgCnt,
srcName=imageName)
imgCnt += 1
images.append([imageName, imageContent])
if not runStatus.run:
self.log.info("Breaking due to exit flag being set")
self.updateDbEntry(sourceUrl, dlState=0)
return
self.log.info("Creating archive with %s images", len(images))
if not images:
self.updateDbEntry(sourceUrl, dlState=-1, tags="error-404")
return
#Write all downloaded files to the archive.
arch = zipfile.ZipFile(fqFName, "w")
for imageName, imageContent in images:
arch.writestr(imageName, imageContent)
arch.close()
dedupState = processDownload.processDownload(seriesName,
fqFName,
deleteDups=True,
includePHash=True,
rowId=link['dbId'])
self.log.info("Done")
filePath, fileName = os.path.split(fqFName)
self.updateDbEntry(sourceUrl,
dlState=2,
downloadPath=filePath,
fileName=fileName,
tags=dedupState)
return
except SystemExit:
print("SystemExit!")
raise
except Exception:
self.log.critical("Failure on retreiving content at %s", sourceUrl)
self.log.critical("Traceback = %s", traceback.format_exc())
self.updateDbEntry(sourceUrl, dlState=-1)
def doDownload(self, linkDict, link):
contentUrl = urllib.parse.urljoin(
self.urlBase, "zipf.php?token={token}&hash={hash}".format(
token=linkDict["contentId"], hash=linkDict["dlToken"]))
print("Fetching: ", contentUrl, " Referer ", linkDict["sourceUrl"])
content, handle = self.wg.getpage(contentUrl,
returnMultiple=True,
addlHeaders={
'Referer': linkDict["sourceUrl"],
"Host": "doujins.com"
})
# self.log.info(len(content))
if handle:
# self.log.info("handle = ", handle)
# self.log.info("geturl", handle.geturl())
urlFileN = urllib.parse.unquote(
urllib.parse.urlparse(handle.geturl())[2].split("/")[-1])
urlFileN = bs4.UnicodeDammit(urlFileN).unicode_markup
urlFileN.encode("utf-8")
# DjMoe is apparently returning "zip.php" for ALL filenames.
# Blargh
if urlFileN == "zipf.php":
urlFileN = ".zip"
fileN = "%s%s" % (linkDict["originName"], urlFileN)
else:
self.log.error("Unknown file extension?")
self.log.error("Unknown file extension?")
self.log.error("Dict filename = %s", linkDict["originName"])
self.log.error("URL filename = %s", urlFileN)
fileN = "%s - %s" % (linkDict["originName"], urlFileN)
fileN = nt.makeFilenameSafe(fileN)
# self.log.info("geturl with processing", fileN)
wholePath = os.path.join(linkDict["dirPath"], fileN)
wholePath = self.insertCountIfFilenameExists(wholePath)
self.log.info("Complete filepath: %s", wholePath)
fp = open(wholePath, "wb")
fp.write(content)
fp.close()
self.log.info("Successfully Saved to path: %s", wholePath)
self.updateDbEntry(linkDict["contentId"],
downloadPath=linkDict["dirPath"],
fileName=fileN)
# Deduper uses the path info for relinking, so we have to dedup the item after updating the downloadPath and fileN
dedupState = processDownload.processDownload(None,
wholePath,
pron=True,
deleteDups=True,
includePHash=True,
rowId=link['dbId'])
self.log.info("Done")
if dedupState:
self.addTags(sourceUrl=linkDict["contentId"], tags=dedupState)
self.updateDbEntry(linkDict["contentId"], dlState=2)
return wholePath
else:
self.updateDbEntry(linkDict["contentId"],
dlState=-1,
downloadPath="ERROR",
fileName="ERROR: FAILED")
# cur.execute('UPDATE djmoe SET downloaded=1 WHERE contentID=?;', (linkDict["contentId"], ))
# cur.execute('UPDATE djmoe SET dlPath=?, dlName=?, itemTags=? WHERE contentID=?;', ("ERROR", 'ERROR: FAILED', "N/A", linkDict["contentId"]))
# self.log.info("fetchall = ", cur.fetchall())
return False
def getLink(self, link):
sourceUrl = link["sourceUrl"]
print("Link", link)
seriesName = link['seriesName']
try:
self.log.info("Should retreive url - %s", sourceUrl)
self.updateDbEntry(sourceUrl, dlState=1)
seriesName = nt.getCanonicalMangaUpdatesName(seriesName)
self.log.info("Downloading = '%s', '%s'", seriesName,
link["originName"])
dlPath, newDir = self.locateOrCreateDirectoryForSeries(seriesName)
if link["flags"] == None:
link["flags"] = ""
if newDir:
self.updateDbEntry(sourceUrl,
flags=" ".join([link["flags"], "haddir"]))
self.conn.commit()
chapterName = nt.makeFilenameSafe(link["originName"])
fqFName = os.path.join(dlPath, chapterName + " [MangaHere].zip")
loop = 1
prefix, ext = os.path.splitext(fqFName)
while os.path.exists(fqFName):
fqFName = "%s (%d)%s" % (prefix, loop, ext)
loop += 1
self.log.info("Saving to archive = %s", fqFName)
images = self.proceduralGetImages(sourceUrl)
self.log.info("Creating archive with %s images", len(images))
if not images:
self.updateDbEntry(sourceUrl, dlState=-1, tags="error-404")
return
#Write all downloaded files to the archive.
arch = zipfile.ZipFile(fqFName, "w")
for imageName, imageContent in images:
arch.writestr(imageName, imageContent)
arch.close()
dedupState = processDownload.processDownload(seriesName,
fqFName,
deleteDups=True,
includePHash=True)
self.log.info("Done")
filePath, fileName = os.path.split(fqFName)
self.updateDbEntry(sourceUrl,
dlState=2,
downloadPath=filePath,
fileName=fileName,
tags=dedupState)
return
except Exception:
self.log.critical("Failure on retreiving content at %s", sourceUrl)
self.log.critical("Traceback = %s", traceback.format_exc())
self.updateDbEntry(sourceUrl, dlState=-1)
raise
def doDownload(self, linkDict):
contentUrl = urllib.parse.urljoin(self.urlBase, "/zip.php?token=%s" % linkDict["contentId"])
content, handle = self.wg.getpage(contentUrl, returnMultiple=True, addlHeaders={'Referer': linkDict["sourceUrl"]})
# self.log.info(len(content))
if handle:
# self.log.info("handle = ", handle)
# self.log.info("geturl", handle.geturl())
urlFileN = urllib.parse.unquote(urllib.parse.urlparse(handle.geturl())[2].split("/")[-1])
urlFileN = bs4.UnicodeDammit(urlFileN).unicode_markup
urlFileN.encode("utf-8")
# DjMoe is apparently returning "zip.php" for ALL filenames.
# Blargh
if urlFileN == "zip.php":
urlFileN = ".zip"
fileN = "%s%s" % (linkDict["originName"], urlFileN)
else:
self.log.error("Unknown file extension?")
self.log.error("Unknown file extension?")
self.log.error("Dict filename = %s", linkDict["originName"])
self.log.error("URL filename = %s", urlFileN)
fileN = "%s - %s" % (linkDict["originName"], urlFileN)
fileN = nt.makeFilenameSafe(fileN)
# self.log.info("geturl with processing", fileN)
wholePath = os.path.join(linkDict["dirPath"], fileN)
self.log.info("Complete filepath: %s", wholePath)
fp = open(wholePath, "wb")
fp.write(content)
fp.close()
self.log.info("Successfully Saved to path: %s", wholePath)
self.updateDbEntry(linkDict["contentId"], downloadPath=linkDict["dirPath"], fileName=fileN)
# Deduper uses the path info for relinking, so we have to dedup the item after updating the downloadPath and fileN
dedupState = processDownload.processDownload(None, wholePath, pron=True, deleteDups=True)
self.log.info( "Done")
if dedupState:
self.addTags(sourceUrl=linkDict["contentId"], tags=dedupState)
self.updateDbEntry(linkDict["contentId"], dlState=2)
self.conn.commit()
else:
self.updateDbEntry(linkDict["contentId"], dlState=-1, downloadPath="ERROR", fileName="ERROR: FAILED")
# cur.execute('UPDATE djmoe SET downloaded=1 WHERE contentID=?;', (linkDict["contentId"], ))
# cur.execute('UPDATE djmoe SET dlPath=?, dlName=?, itemTags=? WHERE contentID=?;', ("ERROR", 'ERROR: FAILED', "N/A", linkDict["contentId"]))
# self.log.info("fetchall = ", cur.fetchall())
self.conn.commit()
def doDownload(self, linkDict):
images = []
containerUrl = linkDict["sourceUrl"]+"/read"
if "http://www.fakku.net/videos/" in containerUrl:
self.log.warning("Cannot download video items.")
self.updateDbEntry(linkDict["sourceUrl"], dlState=-5, downloadPath="Video", fileName="ERROR: Video", lastUpdate=time.time())
return False
if "http://www.fakku.net/games/" in containerUrl:
self.log.warning("Cannot download game items.")
self.updateDbEntry(linkDict["sourceUrl"], dlState=-6, downloadPath="Game", fileName="ERROR: Game", lastUpdate=time.time())
return False
try:
imagePage = self.wg.getpage(containerUrl, addlHeaders={'Referer': linkDict["sourceUrl"]})
except urllib.error.URLError:
self.log.warning("Failure to retreive base page!.")
self.updateDbEntry(linkDict["sourceUrl"], dlState=-1, downloadPath="ERROR", fileName="ERROR", lastUpdate=time.time())
return False
if "This content has been disabled due to a DMCA takedown notice, it is no longer available to download or read online in your region." in imagePage:
self.log.warning("Assholes have DMCAed this item. Not available anymore.")
self.updateDbEntry(linkDict["sourceUrl"], dlState=-4, downloadPath="DMCA", fileName="ERROR: DMCAed", lastUpdate=time.time())
return False
if "Content does not exist." in imagePage:
self.log.warning("Page removed?.")
self.updateDbEntry(linkDict["sourceUrl"], dlState=-7, downloadPath="REMOVED", fileName="ERROR: File removed", lastUpdate=time.time())
return False
# F**k you Fakku, don't include pay-content in your free gallery system.
if "You must purchase this book in order to read it." in imagePage:
self.log.warning("Page removed?.")
self.updateDbEntry(linkDict["sourceUrl"], dlState=-7, downloadPath="REMOVED", fileName="ERROR: Paywalled. ", lastUpdate=time.time())
return False
# F**k you Fakku, don't include pay-content in your free gallery system.
if "Enter your account information below." in imagePage:
self.log.warning("Subscription bullshit?.")
self.updateDbEntry(linkDict["sourceUrl"], dlState=-7, downloadPath="REMOVED", fileName="ERROR: Paywalled. ", lastUpdate=time.time())
return False
# So...... Fakku's reader is completely javascript driven. No (easily) parseable shit here.
# Therefore: WE DECEND TO THE LEVEL OF REGEXBOMINATIONS!
pathFormatterRe = re.compile(r"return '(https://t\.fakku\.net/images/.+/.+/.+?/images/)' \+ x \+ '(\.jpg|\.gif|\.png)';", re.IGNORECASE)
# We need to know how many images there are, but there is no convenient way to access this information.
# The fakku code internally uses the length of the thumbnail array for the number of images, so
# we extract that array, parse it (since it's javascript, variables are JSON, after all), and
# just look at the length ourselves as well.
thumbsListRe = re.compile(r"window\.params\.thumbs = (\[.+?\]);", re.IGNORECASE)
thumbs = thumbsListRe.search(imagePage)
pathFormatter = pathFormatterRe.search(imagePage)
if not thumbs:
self.log.error("Could not find thumbnail array on page!")
self.log.error("URL: '%s'", containerUrl)
if not pathFormatter:
self.log.error("Could not find pathformatter on page!")
self.log.error("URL: '%s'", containerUrl)
items = json.loads(thumbs.group(1))
prefix, postfix = pathFormatter.group(1), pathFormatter.group(2)
print("pathFormatter = ", prefix, prefix)
imageUrls = []
for x in range(len(items)):
item = '{prefix}{num:03d}{postfix}'.format(prefix=pathFormatter.group(1), num=x+1, postfix=pathFormatter.group(2))
imageUrls.append(item)
# print("Prepared image URLs = ")
# print(imageUrls)
# print(linkDict)
images = []
try:
for imageUrl in imageUrls:
imagePath = urllib.parse.urlsplit(imageUrl)[2]
imageFileName = imagePath.split("/")[-1]
if imageUrl.startswith("//"):
imageUrl = "https:" + imageUrl
imageData = self.wg.getpage(imageUrl, addlHeaders={'Referer': containerUrl})
images.append((imageFileName, imageData))
# Find next page
except urllib.error.URLError:
self.log.error("Failure retreiving item images.")
self.updateDbEntry(linkDict["sourceUrl"], dlState=-1, downloadPath="ERROR", fileName="ERROR: Could not retreive images!", lastUpdate=time.time())
self.conn.commit()
return False
# self.log.info(len(content))
if images:
fileN = linkDict["originName"]+".zip"
fileN = nt.makeFilenameSafe(fileN)
# self.log.info("geturl with processing", fileN)
wholePath = os.path.join(linkDict["dirPath"], fileN)
self.log.info("Complete filepath: %s", wholePath)
#Write all downloaded files to the archive.
arch = zipfile.ZipFile(wholePath, "w")
for imageName, imageContent in images:
arch.writestr(imageName, imageContent)
arch.close()
self.log.info("Successfully Saved to path: %s", wholePath)
if not linkDict["tags"]:
linkDict["tags"] = ""
self.updateDbEntry(linkDict["sourceUrl"], downloadPath=linkDict["dirPath"], fileName=fileN)
# Deduper uses the path info for relinking, so we have to dedup the item after updating the downloadPath and fileN
dedupState = processDownload.processDownload(None, wholePath, pron=True, deleteDups=True, includePHash=True)
self.log.info( "Done")
if dedupState:
self.addTags(sourceUrl=linkDict["sourceUrl"], tags=dedupState)
self.updateDbEntry(linkDict["sourceUrl"], dlState=2)
self.conn.commit()
return wholePath
else:
self.updateDbEntry(linkDict["sourceUrl"], dlState=-1, downloadPath="ERROR", fileName="ERROR: FAILED", lastUpdate=time.time())
self.conn.commit()
return False
def getLink(self, link):
sourceUrl = link["sourceUrl"]
seriesName = link["seriesName"]
chapterVol = link["originName"]
sourceUrl = sourceUrl.encode("ascii").decode('ascii')
# print("Item:", link)
try:
self.log.info( "Should retreive url - %s", sourceUrl)
self.updateDbEntry(sourceUrl, dlState=1)
chapterVol, imageUrls = self.getImageUrls(sourceUrl)
if not imageUrls:
self.log.critical("Failure on retreiving content at %s", sourceUrl)
self.log.critical("No images found on page!")
self.updateDbEntry(sourceUrl, dlState=-1)
return
self.log.info("Downloading = '%s', '%s'", seriesName, chapterVol)
dlPath, newDir = self.locateOrCreateDirectoryForSeries(seriesName)
if link["flags"] == None:
link["flags"] = ""
if newDir:
self.updateDbEntry(sourceUrl, flags=" ".join([link["flags"], "haddir"]), originName=chapterVol)
# self.conn.commit()
self.updateDbEntry(sourceUrl, originName=chapterVol)
chapterName = nt.makeFilenameSafe(chapterVol)
fqFName = os.path.join(dlPath, chapterName+"[Sura's Place].zip")
loop = 1
while os.path.exists(fqFName):
fqFName, ext = os.path.splitext(fqFName)
fqFName = "%s (%d)%s" % (fqFName, loop, ext)
loop += 1
self.log.info("Saving to archive = %s", fqFName)
images = []
imgCnt = 1
for imgUrl, referrerUrl in imageUrls:
imageName, imageContent = self.getImage(imgUrl, referrerUrl)
imageName = "{num:03.0f} - {srcName}".format(num=imgCnt, srcName=imageName)
imgCnt += 1
images.append([imageName, imageContent])
if not runStatus.run:
self.log.info( "Breaking due to exit flag being set")
self.updateDbEntry(sourceUrl, dlState=0)
return
self.log.info("Creating archive with %s images", len(images))
if not images:
self.updateDbEntry(sourceUrl, dlState=-1, seriesName=seriesName, originName=chapterVol, tags="error-404")
return
#Write all downloaded files to the archive.
arch = zipfile.ZipFile(fqFName, "w")
for imageName, imageContent in images:
arch.writestr(imageName, imageContent)
arch.close()
dedupState = processDownload.processDownload(seriesName, fqFName, deleteDups=True, includePHash=True)
self.log.info( "Done")
filePath, fileName = os.path.split(fqFName)
self.updateDbEntry(sourceUrl, dlState=2, downloadPath=filePath, fileName=fileName, seriesName=seriesName, originName=chapterVol, tags=dedupState)
return
except Exception:
self.log.critical("Failure on retreiving content at %s", sourceUrl)
self.log.critical("Traceback = %s", traceback.format_exc())
self.updateDbEntry(sourceUrl, dlState=-1)
def doDownload(self, linkDict, link, retag=False):
images = self.fetchImages(linkDict)
# self.log.info(len(content))
if images:
fileN = linkDict['originName'] + ".zip"
fileN = nt.makeFilenameSafe(fileN)
# self.log.info("geturl with processing", fileN)
wholePath = os.path.join(linkDict["dirPath"], fileN)
self.log.info("Complete filepath: %s", wholePath)
#Write all downloaded files to the archive.
chop = len(fileN) - 4
wholePath = "ERROR"
while 1:
try:
fileN = fileN[:chop] + fileN[-4:]
# self.log.info("geturl with processing", fileN)
wholePath = os.path.join(linkDict["dirPath"], fileN)
wholePath = self.insertCountIfFilenameExists(wholePath)
self.log.info("Complete filepath: %s", wholePath)
#Write all downloaded files to the archive.
arch = zipfile.ZipFile(wholePath, "w")
for imageName, imageContent in images:
arch.writestr(imageName, imageContent)
arch.close()
self.log.info("Successfully Saved to path: %s", wholePath)
break
except IOError:
chop = chop - 1
self.log.warn("Truncating file length to %s characters.",
chop)
if not linkDict["tags"]:
linkDict["tags"] = ""
self.updateDbEntry(linkDict["sourceUrl"],
downloadPath=linkDict["dirPath"],
fileName=fileN)
# Deduper uses the path info for relinking, so we have to dedup the item after updating the downloadPath and fileN
dedupState = processDownload.processDownload(
linkDict["seriesName"],
wholePath,
pron=True,
rowId=link['dbId'])
self.log.info("Done")
if dedupState:
self.addTags(sourceUrl=linkDict["sourceUrl"], tags=dedupState)
self.updateDbEntry(linkDict["sourceUrl"], dlState=2)
return wholePath
else:
self.updateDbEntry(linkDict["sourceUrl"],
dlState=-1,
downloadPath="ERROR",
fileName="ERROR: FAILED")
return False
def getLink(self, link):
seriesName = link["seriesName"]
seriesName = seriesName.replace("[", "(").replace("]", "(")
safeBaseName = nt.makeFilenameSafe(link["seriesName"])
if seriesName in nt.dirNameProxy:
self.log.info( "Have target dir for '%s' Dir = '%s'", seriesName, nt.dirNameProxy[seriesName]['fqPath'])
link["targetDir"] = nt.dirNameProxy[seriesName]["fqPath"]
else:
self.log.info( "Don't have target dir for: %s Using default for: %s, full name = %s", seriesName, link["seriesName"], link["originName"])
targetDir = os.path.join(settings.jzSettings["dirs"]['mDlDir'], safeBaseName)
if not os.path.exists(targetDir):
try:
os.makedirs(targetDir)
link["targetDir"] = targetDir
self.updateDbEntry(link["sourceUrl"],flags=" ".join([link["flags"], "newdir"]))
self.conn.commit()
self.conn.commit()
except OSError:
self.log.critical("Directory creation failed?")
self.log.critical(traceback.format_exc())
else:
self.log.warning("Directory not found in dir-dict, but it exists!")
self.log.warning("Directory-Path: %s", targetDir)
link["targetDir"] = targetDir
self.updateDbEntry(link["sourceUrl"],flags=" ".join([link["flags"], "haddir"]))
self.conn.commit()
sourceUrl, originFileName = link["sourceUrl"], link["originName"]
self.log.info( "Should retreive: %s, url - %s", originFileName, sourceUrl)
self.updateDbEntry(sourceUrl, dlState=1)
self.conn.commit()
try:
content, hName = self.getLinkFile(sourceUrl)
except:
self.log.error("Unrecoverable error retreiving content %s", link)
self.log.error("Traceback: %s", traceback.format_exc())
self.updateDbEntry(sourceUrl, dlState=-1)
return
# print("Content type = ", type(content))
# And fix %xx crap
hName = urllib.parse.unquote(hName)
fName = "%s - %s" % (originFileName, hName)
fName = nt.makeFilenameSafe(fName)
fqFName = os.path.join(link["targetDir"], fName)
self.log.info( "SaveName = %s", fqFName)
loop = 1
while os.path.exists(fqFName):
fName = "%s - (%d) - %s" % (originFileName, loop, hName)
fqFName = os.path.join(link["targetDir"], fName)
loop += 1
self.log.info( "Writing file")
filePath, fileName = os.path.split(fqFName)
try:
with open(fqFName, "wb") as fp:
fp.write(content)
except TypeError:
self.log.error("Failure trying to retreive content from source %s", sourceUrl)
self.updateDbEntry(sourceUrl, dlState=-4, downloadPath=filePath, fileName=fileName)
return
#self.log.info( filePath)
ext = os.path.splitext(fileName)[-1]
imageExts = ["jpg", "png", "bmp"]
if not any([ext.endswith(ex) for ex in imageExts]):
dedupState = processDownload.processDownload(False, fqFName, deleteDups=True)
else:
dedupState = ""
self.log.info( "Done")
self.updateDbEntry(sourceUrl, dlState=2, downloadPath=filePath, fileName=fileName, tags=dedupState)
return
def getLink(self, link):
sourceUrl, originFileName = link["sourceUrl"], link["originName"]
self.log.info("Should retreive: %s, url - %s", originFileName,
sourceUrl)
self.updateDbEntry(sourceUrl, dlState=1)
self.conn.commit()
fileUrl = self.getDownloadUrl(sourceUrl)
if fileUrl is None:
self.log.warning("Could not find url!")
self.deleteRowsByValue(sourceUrl=sourceUrl)
return
try:
content, hName = self.getLinkFile(fileUrl, sourceUrl)
except:
self.log.error("Unrecoverable error retreiving content %s", link)
self.log.error("Traceback: %s", traceback.format_exc())
self.updateDbEntry(sourceUrl, dlState=-1)
return
# print("Content type = ", type(content))
# And fix %xx crap
hName = urllib.parse.unquote(hName)
fName = "%s - %s" % (originFileName, hName)
fName = nt.makeFilenameSafe(fName)
fqFName = os.path.join(link["targetDir"], fName)
self.log.info("SaveName = %s", fqFName)
loop = 1
while os.path.exists(fqFName):
fName = "%s - (%d) - %s" % (originFileName, loop, hName)
fqFName = os.path.join(link["targetDir"], fName)
loop += 1
self.log.info("Writing file")
filePath, fileName = os.path.split(fqFName)
try:
with open(fqFName, "wb") as fp:
fp.write(content)
except TypeError:
self.log.error("Failure trying to retreive content from source %s",
sourceUrl)
return
#self.log.info( filePath)
dedupState = processDownload.processDownload(link["seriesName"],
fqFName,
deleteDups=True,
includePHash=True)
self.log.info("Done")
self.updateDbEntry(sourceUrl,
dlState=2,
downloadPath=filePath,
fileName=fileName,
tags=dedupState)
return
def getLink(self, link):
sourceUrl = link["sourceUrl"]
seriesName = link["seriesName"]
originFileName = link["originName"]
self.updateDbEntry(sourceUrl, dlState=1)
self.log.info("Downloading = '%s', '%s'", seriesName, originFileName)
dlPath, newDir = self.locateOrCreateDirectoryForSeries(seriesName)
if link["flags"] == None:
link["flags"] = ""
if newDir:
self.updateDbEntry(sourceUrl,
flags=" ".join([link["flags"], "haddir"]))
self.conn.commit()
try:
content, headerName = self.getLinkFile(sourceUrl)
except:
self.log.error("Unrecoverable error retreiving content %s", link)
self.log.error("Traceback: %s", traceback.format_exc())
self.updateDbEntry(sourceUrl, dlState=-1)
return
headerName = urllib.parse.unquote(headerName)
fName = "%s - %s" % (originFileName, headerName)
fName = nt.makeFilenameSafe(fName)
fName, ext = os.path.splitext(fName)
fName = "%s [CXC Scans]%s" % (fName, ext)
fqFName = os.path.join(dlPath, fName)
self.log.info("SaveName = %s", fqFName)
loop = 1
while os.path.exists(fqFName):
fName, ext = os.path.splitext(fName)
fName = "%s (%d)%s" % (fName, loop, ext)
fqFName = os.path.join(link["targetDir"], fName)
loop += 1
self.log.info("Writing file")
filePath, fileName = os.path.split(fqFName)
try:
with open(fqFName, "wb") as fp:
fp.write(content)
except TypeError:
self.log.error("Failure trying to retreive content from source %s",
sourceUrl)
self.updateDbEntry(sourceUrl,
dlState=-4,
downloadPath=filePath,
fileName=fileName)
return
#self.log.info( filePath)
dedupState = processDownload.processDownload(seriesName,
fqFName,
deleteDups=True)
self.log.info("Done")
self.updateDbEntry(sourceUrl,
dlState=2,
downloadPath=filePath,
fileName=fileName,
tags=dedupState)
return
def getLink(self, link):
seriesName = link["seriesName"]
seriesName = seriesName.replace("[", "(").replace("]", "(")
safeBaseName = nt.makeFilenameSafe(link["seriesName"])
if seriesName in nt.dirNameProxy:
self.log.info("Have target dir for '%s' Dir = '%s'", seriesName,
nt.dirNameProxy[seriesName]['fqPath'])
link["targetDir"] = nt.dirNameProxy[seriesName]["fqPath"]
else:
self.log.info(
"Don't have target dir for: %s Using default for: %s, full name = %s",
seriesName, link["seriesName"], link["originName"])
targetDir = os.path.join(settings.jzSettings["dirs"]['mDlDir'],
safeBaseName)
if not os.path.exists(targetDir):
try:
os.makedirs(targetDir)
link["targetDir"] = targetDir
self.updateDbEntry(link["sourceUrl"],
flags=" ".join(
[link["flags"], "newdir"]))
self.conn.commit()
self.conn.commit()
except OSError:
self.log.critical("Directory creation failed?")
self.log.critical(traceback.format_exc())
else:
self.log.warning(
"Directory not found in dir-dict, but it exists!")
self.log.warning("Directory-Path: %s", targetDir)
link["targetDir"] = targetDir
self.updateDbEntry(link["sourceUrl"],
flags=" ".join([link["flags"], "haddir"]))
self.conn.commit()
sourceUrl, originFileName = link["sourceUrl"], link["originName"]
self.log.info("Should retreive: %s, url - %s", originFileName,
sourceUrl)
self.updateDbEntry(sourceUrl, dlState=1)
self.conn.commit()
try:
content, hName = self.getLinkFile(sourceUrl)
except:
self.log.error("Unrecoverable error retreiving content %s", link)
self.log.error("Traceback: %s", traceback.format_exc())
self.updateDbEntry(sourceUrl, dlState=-1)
return
# print("Content type = ", type(content))
# And fix %xx crap
hName = urllib.parse.unquote(hName)
fName = "%s - %s" % (originFileName, hName)
fName = nt.makeFilenameSafe(fName)
fqFName = os.path.join(link["targetDir"], fName)
self.log.info("SaveName = %s", fqFName)
loop = 1
while os.path.exists(fqFName):
fName = "%s - (%d) - %s" % (originFileName, loop, hName)
fqFName = os.path.join(link["targetDir"], fName)
loop += 1
self.log.info("Writing file")
filePath, fileName = os.path.split(fqFName)
try:
with open(fqFName, "wb") as fp:
fp.write(content)
except TypeError:
self.log.error("Failure trying to retreive content from source %s",
sourceUrl)
self.updateDbEntry(sourceUrl,
dlState=-4,
downloadPath=filePath,
fileName=fileName)
return
#self.log.info( filePath)
ext = os.path.splitext(fileName)[-1]
imageExts = ["jpg", "png", "bmp"]
if not any([ext.endswith(ex) for ex in imageExts]):
dedupState = processDownload.processDownload(False,
fqFName,
deleteDups=True)
else:
dedupState = ""
self.log.info("Done")
self.updateDbEntry(sourceUrl,
dlState=2,
downloadPath=filePath,
fileName=fileName,
tags=dedupState)
return
def getLink(self, link):
sourceUrl = link["sourceUrl"]
seriesName = link["seriesName"]
chapterVol = link["originName"]
try:
self.log.info( "Should retreive url - %s", sourceUrl)
self.updateDbEntry(sourceUrl, dlState=1)
imageUrls = self.getImageUrls(sourceUrl)
if not imageUrls:
self.log.critical("Failure on retreiving content at %s", sourceUrl)
self.log.critical("Page not found - 404")
self.updateDbEntry(sourceUrl, dlState=-1)
return
self.log.info("Downloading = '%s', '%s' ('%s images)", seriesName, chapterVol, len(imageUrls))
dlPath, newDir = self.locateOrCreateDirectoryForSeries(seriesName)
if link["flags"] == None:
link["flags"] = ""
if newDir:
self.updateDbEntry(sourceUrl, flags=" ".join([link["flags"], "haddir"]))
self.conn.commit()
chapterName = nt.makeFilenameSafe(chapterVol)
fqFName = os.path.join(dlPath, chapterName+"["+self.groupName+"].zip")
loop = 1
while os.path.exists(fqFName):
fqFName, ext = os.path.splitext(fqFName)
fqFName = "%s (%d)%s" % (fqFName, loop, ext)
loop += 1
self.log.info("Saving to archive = %s", fqFName)
images = []
for imageName, imgUrl, referrerUrl in imageUrls:
dummy_imageName, imageContent = self.getImage(imgUrl, referrerUrl)
images.append([imageName, imageContent])
if not runStatus.run:
self.log.info( "Breaking due to exit flag being set")
self.updateDbEntry(sourceUrl, dlState=0)
return
self.log.info("Creating archive with %s images", len(images))
if not images:
self.updateDbEntry(sourceUrl, dlState=-1, seriesName=seriesName, originName=chapterVol, tags="error-404")
return
#Write all downloaded files to the archive.
arch = zipfile.ZipFile(fqFName, "w")
for imageName, imageContent in images:
arch.writestr(imageName, imageContent)
arch.close()
filePath, fileName = os.path.split(fqFName)
self.updateDbEntry(sourceUrl, downloadPath=filePath, fileName=fileName)
dedupState = processDownload.processDownload(seriesName, fqFName, deleteDups=True)
self.log.info( "Done")
self.updateDbEntry(sourceUrl, dlState=2, downloadPath=filePath, fileName=fileName, seriesName=seriesName, originName=chapterVol, tags=dedupState)
return
except Exception:
self.log.critical("Failure on retreiving content at %s", sourceUrl)
self.log.critical("Traceback = %s", traceback.format_exc())
self.updateDbEntry(sourceUrl, dlState=-1)
def getLink(self, link):
seriesName = link["seriesName"]
seriesName = seriesName.replace("[", "(").replace("]", "(")
safeBaseName = nt.makeFilenameSafe(link["seriesName"])
if seriesName in nt.dirNameProxy:
self.log.info( "Have target dir for '%s' Dir = '%s'", seriesName, nt.dirNameProxy[seriesName]['fqPath'])
link["targetDir"] = nt.dirNameProxy[seriesName]["fqPath"]
else:
self.log.info( "Don't have target dir for: %s Using default for: %s, full name = %s", seriesName, link["seriesName"], link["originName"])
targetDir = os.path.join(settings.mkSettings["dirs"]['mDlDir'], safeBaseName)
if not os.path.exists(targetDir):
try:
os.makedirs(targetDir)
link["targetDir"] = targetDir
self.updateDbEntry(link["sourceUrl"],flags=" ".join([link["flags"], "newdir"]))
except OSError:
self.log.critical("Directory creation failed?")
self.log.critical(traceback.format_exc())
else:
self.log.warning("Directory not found in dir-dict, but it exists!")
self.log.warning("Directory-Path: %s", targetDir)
link["targetDir"] = targetDir
self.updateDbEntry(link["sourceUrl"],flags=" ".join([link["flags"], "haddir"]))
sourceUrl, originFileName = link["sourceUrl"], link["originName"]
self.log.info( "Should retreive: %s, url - %s", originFileName, sourceUrl)
self.updateDbEntry(sourceUrl, dlState=1)
try:
content, hName = self.getLinkFile(sourceUrl)
except:
self.log.error("Unrecoverable error retreiving content %s", link)
self.log.error("Traceback: %s", traceback.format_exc())
self.updateDbEntry(sourceUrl, dlState=-1)
return
# print("Content type = ", type(content))
# And fix %xx crap
hName = urllib.parse.unquote(hName)
fName = "%s - %s" % (originFileName, hName)
fName = nt.makeFilenameSafe(fName)
fqFName = os.path.join(link["targetDir"], fName)
self.log.info( "SaveName = %s", fqFName)
loop = 1
while os.path.exists(fqFName):
fName = "%s - (%d) - %s" % (originFileName, loop, hName)
fqFName = os.path.join(link["targetDir"], fName)
loop += 1
self.log.info( "Writing file")
filePath, fileName = os.path.split(fqFName)
try:
chop = len(fileName) - 4
wholePath = "ERROR"
while 1:
try:
fileName = fileName[:chop]+fileName[-4:]
# self.log.info("geturl with processing", fileName)
wholePath = os.path.join(filePath, fileName)
self.log.info("Complete filepath: %s", wholePath)
#Write all downloaded files to the archive.
with open(wholePath, "wb") as fp:
fp.write(content)
self.log.info("Successfully Saved to path: %s", wholePath)
break
except IOError:
chop = chop - 1
if chop < 200:
raise RuntimeError("Don't know what's going on, but a file truncated too far!")
self.log.warn("Truncating file length to %s characters.", chop)
except TypeError:
self.log.error("Failure trying to retreive content from source %s", sourceUrl)
self.updateDbEntry(sourceUrl, dlState=-4, downloadPath=filePath, fileName=fileName)
return
#self.log.info( filePath)
ext = os.path.splitext(fileName)[-1]
imageExts = ["jpg", "png", "bmp"]
if not any([ext.endswith(ex) for ex in imageExts]):
# We don't want to upload the file we just downloaded, so specify doUpload as false.
dedupState = processDownload.processDownload(False, fqFName, deleteDups=True, doUpload=False, rowId=link['dbId'])
else:
dedupState = ""
self.log.info( "Done")
self.updateDbEntry(sourceUrl, dlState=2, downloadPath=filePath, fileName=fileName, tags=dedupState)
return
def getLink(self, link):
sourceUrl = link["sourceUrl"]
try:
self.log.info( "Should retreive url - %s", sourceUrl)
self.updateDbEntry(sourceUrl, dlState=1)
seriesName, chapterVol, imageUrls = self.getContainerPages(sourceUrl)
if not seriesName and not chapterVol and not imageUrls:
self.log.critical("Failure on retreiving content at %s", sourceUrl)
self.log.critical("Page not found - 404")
self.updateDbEntry(sourceUrl, dlState=-1)
return
self.log.info("Downloading = '%s', '%s'", seriesName, chapterVol)
dlPath, newDir = self.locateOrCreateDirectoryForSeries(seriesName)
if link["flags"] == None:
link["flags"] = ""
if newDir:
self.updateDbEntry(sourceUrl, flags=" ".join([link["flags"], "haddir"]))
self.conn.commit()
chapterNameRaw = " - ".join((seriesName, chapterVol))
chapterName = nt.makeFilenameSafe(chapterNameRaw)
fqFName = os.path.join(dlPath, chapterName+" [batoto].zip")
loop = 1
while os.path.exists(fqFName):
fName = "%s - (%d).zip" % (chapterName, loop)
fqFName = os.path.join(dlPath, fName)
loop += 1
self.log.info("Saving to archive = %s", fqFName)
images = []
for imgUrl in imageUrls:
self.log.info("Fetching content for item: %s", imgUrl)
imageName, imageContent = self.getImage(imgUrl, "http://bato.to/reader")
images.append([imageName, imageContent])
if not runStatus.run:
self.log.info( "Breaking due to exit flag being set")
self.updateDbEntry(sourceUrl, dlState=0)
return
self.log.info("Creating archive with %s images", len(images))
if not images:
self.updateDbEntry(sourceUrl, dlState=-1, seriesName=seriesName, originName=chapterNameRaw, tags="error-404")
return
#Write all downloaded files to the archive.
arch = zipfile.ZipFile(fqFName, "w")
for imageName, imageContent in images:
arch.writestr(imageName, imageContent)
arch.close()
dedupState = processDownload.processDownload(seriesName, fqFName, deleteDups=True, includePHash=False)
self.log.info( "Done")
filePath, fileName = os.path.split(fqFName)
self.updateDbEntry(sourceUrl, dlState=2, downloadPath=filePath, fileName=fileName, seriesName=seriesName, originName=chapterNameRaw, tags=dedupState)
return
except Exception:
self.log.critical("Failure on retreiving content at %s", sourceUrl)
self.log.critical("Traceback = %s", traceback.format_exc())
self.updateDbEntry(sourceUrl, dlState=-1)
def doDownload(self, linkDict):
images = []
title = None
nextPage = linkDict["dlLink"]
while nextPage:
gatewayPage = self.wg.getpage(nextPage, addlHeaders={'Referer': linkDict["sourceUrl"]})
soup = bs4.BeautifulSoup(gatewayPage, "lxml")
titleCont = soup.find("div", class_="image-menu")
title = titleCont.h1.get_text()
title = title.replace("Reading ", "")
title, dummy = title.rsplit(" Page ", 1)
title = title.strip()
imageUrl = soup.find("img", class_="b")
imageUrl = urllib.parse.urljoin(self.urlBase, imageUrl["src"])
imagePath = urllib.parse.urlsplit(imageUrl)[2]
imageFileName = imagePath.split("/")[-1]
imageData = self.wg.getpage(imageUrl, addlHeaders={'Referer': nextPage})
images.append((imageFileName, imageData))
# Find next page
nextPageLink = soup.find("a", class_="link-next")
if not nextPageLink:
nextPage = None
elif nextPageLink["href"].startswith("/finish/"): # Break on the last image.
nextPage = None
else:
nextPage = urllib.parse.urljoin(self.urlBase, nextPageLink["href"])
# self.log.info(len(content))
if images and title:
fileN = title+".zip"
fileN = nt.makeFilenameSafe(fileN)
# self.log.info("geturl with processing", fileN)
wholePath = os.path.join(linkDict["dirPath"], fileN)
self.log.info("Complete filepath: %s", wholePath)
#Write all downloaded files to the archive.
try:
arch = zipfile.ZipFile(wholePath, "w")
except OSError:
title = title.encode('ascii','ignore').decode('ascii')
fileN = title+".zip"
fileN = nt.makeFilenameSafe(fileN)
wholePath = os.path.join(linkDict["dirPath"], fileN)
arch = zipfile.ZipFile(wholePath, "w")
for imageName, imageContent in images:
arch.writestr(imageName, imageContent)
arch.close()
self.log.info("Successfully Saved to path: %s", wholePath)
self.updateDbEntry(linkDict["sourceUrl"], downloadPath=linkDict["dirPath"], fileName=fileN)
# Deduper uses the path info for relinking, so we have to dedup the item after updating the downloadPath and fileN
dedupState = processDownload.processDownload(None, wholePath, pron=True, deleteDups=True, includePHash=True)
self.log.info( "Done")
if dedupState:
self.addTags(sourceUrl=linkDict["sourceUrl"], tags=dedupState)
self.updateDbEntry(linkDict["sourceUrl"], dlState=2)
self.conn.commit()
return wholePath
else:
self.updateDbEntry(linkDict["sourceUrl"], dlState=-1, downloadPath="ERROR", fileName="ERROR: FAILED")
self.conn.commit()
return False