def get_remote_filesize(url, referer, config, notifier=None):
if notifier is None:
notifier = PixivHelper.dummy_notifier
PixivHelper.print_and_log(None, 'Getting remote filesize...')
# open with HEAD method, might be expensive
req = PixivHelper.create_custom_request(url, config, referer, head=True)
file_size = -1
try:
br = PixivBrowserFactory.getBrowser(config=config)
res = br.open_novisit(req)
content_length = res.info()['Content-Length']
if content_length is not None:
file_size = int(content_length)
else:
PixivHelper.print_and_log('info', "\tNo file size information!")
res.close()
except KeyError:
PixivHelper.print_and_log('info', "\tNo file size information!")
except mechanize.HTTPError as e:
# fix Issue #503
# handle http errors explicit by code
if int(e.code) in (404, 500):
PixivHelper.print_and_log('info', "\tNo file size information!")
else:
raise
PixivHelper.print_and_log(
None,
f"Remote filesize = {PixivHelper.size_in_str(file_size)} ({file_size} Bytes)"
)
return file_size
def process_manga_series(caller,
config,
manga_series_id: int,
start_page: int = 1,
end_page: int = 0,
notifier=None,
job_option=None):
if notifier is None:
notifier = PixivHelper.dummy_notifier
try:
msg = Fore.YELLOW + Style.NORMAL + f'Processing Manga Series Id: {manga_series_id}' + Style.RESET_ALL
PixivHelper.print_and_log(None, msg)
notifier(type="MANGA_SERIES", message=msg)
if start_page != 1:
PixivHelper.print_and_log('info', 'Start Page: ' + str(start_page))
if end_page != 0:
PixivHelper.print_and_log('info', 'End Page: ' + str(end_page))
flag = True
current_page = start_page
while flag:
manga_series = PixivBrowserFactory.getBrowser().getMangaSeries(manga_series_id, current_page)
for (image_id, order) in manga_series.pages_with_order:
result = process_image(caller,
config,
artist=manga_series.artist,
image_id=image_id,
user_dir='',
bookmark=False,
search_tags='',
title_prefix="",
bookmark_count=-1,
image_response_count=-1,
notifier=notifier,
job_option=job_option,
useblacklist=True,
manga_series_order=order,
manga_series_parent=manga_series)
PixivHelper.wait(result, config)
current_page += 1
if manga_series.is_last_page:
PixivHelper.print_and_log('info', f'Last Page {manga_series.current_page}')
flag = False
if current_page > end_page and end_page != 0:
PixivHelper.print_and_log('info', f'End Page reached {end_page}')
flag = False
if manga_series.pages_with_order is None or len(manga_series.pages_with_order) == 0:
PixivHelper.print_and_log('info', 'No more works.')
flag = False
except Exception as ex:
if isinstance(ex, KeyboardInterrupt):
raise
caller.ERROR_CODE = getattr(ex, 'errorCode', -1)
exc_type, exc_value, exc_traceback = sys.exc_info()
traceback.print_exception(exc_type, exc_value, exc_traceback)
PixivHelper.print_and_log('error', f'Error at process_manga_series(): {manga_series_id}')
PixivHelper.print_and_log('error', f'Exception: {sys.exc_info()}')
raise
def ParseMangaImagesNew(self, page, _br):
urls = []
# mangaSection = page.find("section", attrs={'class': 'manga'})
# links = mangaSection.findAll('a')
# pattern /member_illust.php?mode=manga_big&illust_id=46279245&page=0
if _br is None:
import PixivBrowserFactory
_br = PixivBrowserFactory.getExistingBrowser()
total = page.find("span", attrs={'class': 'total'})
if total is not None:
self.imageCount = int(total.string)
for currPage in range(0, self.imageCount):
expected_url = '/member_illust.php?mode=manga_big&illust_id=' + str(self.imageId) + '&page=' + str(currPage)
try:
href = _br.fixUrl(expected_url)
print "Fetching big image page:", href
bigPage = _br.getPixivPage(url=href,
referer="http://www.pixiv.net/member_illust.php?mode=manga&illust_id=" + str(
self.imageId))
bigImg = bigPage.find('img')
imgUrl = bigImg["src"]
# http://i2.pixiv.net/img-original/img/2013/12/27/01/51/37/40538869_p7.jpg
print "Found: ", imgUrl
urls.append(imgUrl)
bigImg.decompose()
bigPage.decompose()
del bigImg
del bigPage
except Exception as ex:
print ex
return urls
def ParseMangaImagesNew(self, page, _br):
urls = []
mangaSection = page.find("section", attrs={'class':'manga'})
links = mangaSection.findAll('a')
## /member_illust.php?mode=manga_big&illust_id=46279245&page=0
if _br is None:
import PixivBrowserFactory
_br = PixivBrowserFactory.getExistingBrowser()
for link in links:
try:
href = _br.fixUrl(link["href"])
print "Fetching big image page:", href
bigPage = _br.getPixivPage(url=href, referer = "http://www.pixiv.net/member_illust.php?mode=manga&illust_id=" + str(self.imageId))
bigImg = bigPage.find('img')
imgUrl = bigImg["src"]
print "Found: ", imgUrl
urls.append(imgUrl)
bigImg.decompose()
bigPage.decompose()
del bigImg
del bigPage
except Exception as ex:
print ex
total = page.find("span", attrs={'class':'total'})
if total is not None:
self.imageCount = int(total.string)
if self.imageCount != len(urls):
raise PixivException("Different images count: " + str(self.imageCount) + " != " + str(len(urls)))
return urls
def ParseMangaImagesNew(self, page):
urls = []
mangaSection = page.find("section", attrs={'class':'manga'})
links = mangaSection.findAll('a')
## /member_illust.php?mode=manga_big&illust_id=46279245&page=0
import PixivBrowserFactory
_br = PixivBrowserFactory.getExistingBrowser()
for link in links:
try:
href = _br.fixUrl(link["href"])
print "Fetching big image page:", href
bigPage = _br.getPixivPage(url=href, referer = "http://www.pixiv.net/member_illust.php?mode=manga&illust_id=" + str(self.imageId))
bigImg = bigPage.find('img')
imgUrl = bigImg["src"]
print "Found: ", imgUrl
urls.append(imgUrl)
bigImg.decompose()
bigPage.decompose()
del bigImg
del bigPage
except Exception as ex:
print ex
total = page.find("span", attrs={'class':'total'})
if total is not None:
self.imageCount = int(total.string)
if self.imageCount != len(urls):
raise PixivException("Different images count: " + str(self.imageCount) + " != " + str(len(urls)))
return urls
def ParseMangaImagesNew(self, page, _br):
urls = []
mangaSection = page.find("section", attrs={'class': 'manga'})
links = mangaSection.findAll('a')
# pattern /member_illust.php?mode=manga_big&illust_id=46279245&page=0
if _br is None:
import PixivBrowserFactory
_br = PixivBrowserFactory.getExistingBrowser()
total = page.find("span", attrs={'class': 'total'})
if total is not None:
self.imageCount = int(total.string)
for currPage in range(0, self.imageCount):
expected_url = '/member_illust.php?mode=manga_big&illust_id=' + str(self.imageId) + '&page=' + str(currPage)
try:
href = _br.fixUrl(expected_url)
print "Fetching big image page:", href
bigPage = _br.getPixivPage(url=href,
referer="http://www.pixiv.net/member_illust.php?mode=manga&illust_id=" + str(
self.imageId))
bigImg = bigPage.find('img')
imgUrl = bigImg["src"]
# http://i2.pixiv.net/img-original/img/2013/12/27/01/51/37/40538869_p7.jpg
print "Found: ", imgUrl
urls.append(imgUrl)
bigImg.decompose()
bigPage.decompose()
del bigImg
del bigPage
except Exception as ex:
print ex
return urls
def perform_download(url,
file_size,
filename,
overwrite,
config,
referer=None,
notifier=None):
if notifier is None:
notifier = PixivHelper.dummy_notifier
if referer is None:
referer = config.referer
# actual download
PixivHelper.print_and_log(None, '\rStart downloading...', newline=False)
# fetch filesize
req = PixivHelper.create_custom_request(url, config, referer)
br = PixivBrowserFactory.getBrowser(config=config)
res = br.open_novisit(req)
if file_size < 0: # final check before download for download progress bar.
try:
content_length = res.info()['Content-Length']
if content_length is not None:
file_size = int(content_length)
except KeyError:
file_size = -1
PixivHelper.print_and_log('info', "\tNo file size information!")
(downloadedSize,
filename) = PixivHelper.download_image(url, filename, res, file_size,
overwrite)
res.close()
gc.collect()
return (downloadedSize, filename)
def check_version(br, config=None):
if br is None:
import PixivBrowserFactory
br = PixivBrowserFactory.getBrowser(config=config)
result = br.open_with_retry(
"https://raw.githubusercontent.com/Nandaka/PixivUtil2/master/PixivConstant.py",
retry=3)
page = result.read().decode('utf-8')
result.close()
latest_version_full = re.findall(r"PIXIVUTIL_VERSION = '(\d+)(.*)'", page)
latest_version_int = int(latest_version_full[0][0])
curr_version_int = int(
re.findall(r"(\d+)", PixivConstant.PIXIVUTIL_VERSION)[0])
is_beta = True if latest_version_full[0][1].find("beta") >= 0 else False
if is_beta and not config.notifyBetaVersion:
return
url = "https://github.com/Nandaka/PixivUtil2/releases"
if latest_version_int > curr_version_int:
if is_beta:
print_and_log(
"info", "New beta version available: {0}".format(
latest_version_full[0]))
else:
print_and_log(
"info",
"New version available: {0}".format(latest_version_full[0]))
if config.openNewVersion:
webbrowser.open_new(url)
def process_sketch_artists(caller,
config,
artist_id,
start_page=1,
end_page=0,
title_prefix=None):
config.loadConfig(path=caller.configfile)
br = PixivBrowserFactory.getBrowser()
if title_prefix is None:
title_prefix = f"Pixiv Sketch - Processing Artist Id: {artist_id}"
else:
title_prefix = f"{title_prefix} Pixiv Sketch - Processing Artist Id: {artist_id}"
caller.set_console_title(title_prefix)
msg = Fore.YELLOW + Style.NORMAL + f'Processing Artist Id: {artist_id} for PixivSketch' + Style.RESET_ALL
PixivHelper.print_and_log(None, msg)
try:
artist = br.sketch_get_posts_by_artist_id(artist_id, end_page)
# check if have posts
if len(artist.posts) == 0:
PixivHelper.print_and_log('warn',
f'No images for Artist Id: {artist_id}')
return
POST_PER_PAGE = 10
start_idx = POST_PER_PAGE * (start_page - 1)
end_idx = POST_PER_PAGE * (end_page)
if end_page == 0 or end_idx > len(artist.posts):
end_idx = len(artist.posts)
msg = Fore.YELLOW + Style.NORMAL + f'Processing from post #{start_idx} to #{end_idx}' + Style.RESET_ALL
PixivHelper.print_and_log(None, msg)
post_to_process = artist.posts[start_idx:end_idx]
current_post = 1
for item in post_to_process:
caller.set_console_title(
f"{title_prefix} - Post {current_post} of {len(post_to_process)}"
)
PixivHelper.print_and_log(None, f'Post #: {current_post}')
PixivHelper.print_and_log('info', f'Post ID : {item.imageId}')
tags_str = ', '.join(item.imageTags)
PixivHelper.print_and_log('info', f'Tags : {tags_str}')
download_post(caller, config, item)
current_post = current_post + 1
except PixivException as pex:
PixivHelper.print_and_log(
"error",
f"Failed to process PixivSketch for {artist_id}, maybe doesn't have PixivSketch? ==> {pex.message}"
)
except Exception as ex:
if isinstance(ex, KeyboardInterrupt):
raise
caller.ERROR_CODE = getattr(ex, 'errorCode', -1)
exc_type, exc_value, exc_traceback = sys.exc_info()
traceback.print_exception(exc_type, exc_value, exc_traceback)
PixivHelper.print_and_log(
'error', f'Error at process_sketch_artists(): {artist_id}')
PixivHelper.print_and_log('error', f'Exception: {sys.exc_info()}')
def check_version():
import PixivBrowserFactory
br = PixivBrowserFactory.getBrowser()
result = br.open_with_retry("https://raw.githubusercontent.com/Nandaka/PixivUtil2/master/PixivConstant.py", retry=3)
page = result.read()
latest_version_full = re.findall(r"PIXIVUTIL_VERSION = '(\d+)(.*)'", page)
latest_version_int = int(latest_version_full[0][0])
curr_version_int = int(re.findall(r"(\d+)", PixivConstant.PIXIVUTIL_VERSION)[0])
is_beta = True if latest_version_full[0][1].find("beta") >= 0 else False
if latest_version_int > curr_version_int:
print_and_log("info", "New version available: {0}".format(latest_version_full[0]))
def check_version():
import PixivBrowserFactory
br = PixivBrowserFactory.getBrowser()
result = br.open_with_retry("https://raw.githubusercontent.com/Nandaka/PixivUtil2/master/PixivConstant.py", retry=3)
page = result.read()
latest_version_full = re.findall(r"PIXIVUTIL_VERSION = '(\d+)(.*)'", page)
latest_version_int = int(latest_version_full[0][0])
curr_version_int = int(re.findall(r"(\d+)", PixivConstant.PIXIVUTIL_VERSION)[0])
is_beta = True if latest_version_full[0][1].find("beta") >= 0 else False
if latest_version_int > curr_version_int:
print_and_log("info", "New version available: {0}".format(latest_version_full[0]))
def process_fanbox_artist_by_id(caller, config, artist_id, end_page, title_prefix=""):
config.loadConfig(path=caller.configfile)
br = PixivBrowserFactory.getBrowser()
caller.set_console_title(title_prefix)
try:
artist = br.fanboxGetArtistById(artist_id)
except PixivException as pex:
PixivHelper.print_and_log("error", "Error gettting FANBOX artist by id: {0} ==> {1}".format(artist_id, pex.message))
return
current_page = 1
next_url = None
image_count = 1
while True:
PixivHelper.print_and_log("info", "Processing {0}, page {1}".format(artist, current_page))
caller.set_console_title(f"{title_prefix} FANBOX Artist {artist}, page {current_page}")
try:
posts = br.fanboxGetPostsFromArtist(artist, next_url)
except PixivException as pex:
PixivHelper.print_and_log("error", "Error getting FANBOX posts of artist: {0} ==> {1}".format(artist, pex.message))
break
for post in posts:
print("#{0}".format(image_count))
post.printPost()
# images
if post.type in PixivModelFanbox.FanboxPost._supportedType:
try:
process_fanbox_post(caller, config, post, artist)
except KeyboardInterrupt:
choice = input("Keyboard Interrupt detected, continue to next post (Y/N)").rstrip("\r")
if choice.upper() == 'N':
PixivHelper.print_and_log("info", f"FANBOX artist: {artist}, processing aborted")
break
else:
continue
image_count += 1
PixivHelper.wait(config)
if not artist.hasNextPage:
PixivHelper.print_and_log("info", "No more post for {0}".format(artist))
break
current_page += 1
if end_page > 0 and current_page > end_page:
PixivHelper.print_and_log("info", "Reaching page limit for {0}, limit {1}".format(artist, end_page))
break
next_url = artist.nextUrl
if next_url is None:
PixivHelper.print_and_log("info", "No more next page for {0}".format(artist))
break
def handle_members(caller, job, job_name, job_option):
member_ids = list()
if "member_ids" in job:
print("Multi Member IDs")
member_ids = job["member_ids"]
elif "member_id" in job:
member_id = job["member_id"]
member_ids.append(member_id)
else:
print(f"No member_id or member_ids found in {job_name}!")
return
start_page = 1
if "start_page" in job:
start_page = int(job["start_page"])
end_page = 0
if "end_page" in job:
end_page = int(job["end_page"])
from_bookmark = False
if "from_bookmark" in job:
from_bookmark = bool(job["from_bookmark"])
tags = None
if "tags" in job and len(job["tags"]) > 0:
tags = job["tags"]
include_sketch = False
if "include_sketch" in job and len(job["include_sketch"]) > 0:
include_sketch = bool(job["include_sketch"])
for member_id in member_ids:
PixivArtistHandler.process_member(caller,
job_option.config,
member_id=member_id,
user_dir=job_option.config.rootDirectory,
page=start_page,
end_page=end_page,
bookmark=from_bookmark,
tags=tags,
title_prefix=f"{job_name} ")
if include_sketch:
# fetching artist token...
(artist_model, _) = PixivBrowserFactory.getBrowser().getMemberPage(member_id)
PixivSketchHandler.process_sketch_artists(caller,
job_option.config,
artist_model.artistToken,
start_page=start_page,
end_page=end_page,
title_prefix=f"{job_name} ")
def ParseToken(self, page, fromImage=False):
if self.artistAvatar.endswith("no_profile.png"):
if fromImage:
temp = page.findAll(attrs={'class':'works_display'})
token = str(temp[0].find('img')['src'])
return token.split('/')[-2]
else :
artistToken = None
try:
temp = page.find(attrs={'class':'display_works linkStyleWorks'}).ul
if temp != None:
tokens = temp.findAll('img', attrs={'class':'_thumbnail'})
for token in tokens:
try:
tempImage = token['data-src']
except:
tempImage = token['src']
folders = tempImage.split('/')
## skip http://i2.pixiv.net/img-inf/img/2013/04/07/03/08/21/34846113_s.jpg
if folders[3] == 'img-inf':
continue
artistToken = folders[-2]
if artistToken != 'common':
return artistToken
## all thumb images are using img-inf
## take the first image and check the medium page
if artistToken == None or artistToken != 'common':
PixivHelper.GetLogger().info("Unable to parse Artist Token from image list, try to parse from the first image")
import PixivBrowserFactory, PixivConstant
firstImageLink = temp.find('a', attrs={'class':'work'})['href']
if firstImageLink.find("http") != 0:
firstImageLink = PixivConstant.PIXIV_URL + firstImageLink
PixivHelper.GetLogger().info("Using: " + firstImageLink + " for parsing artist token")
imagePage = PixivBrowserFactory.getBrowser().open(firstImageLink)
imageResult = BeautifulSoup(imagePage.read())
token = str(imageResult.find(attrs={'class':'works_display'}).find('img')['src'])
return token.split('/')[-2]
raise PixivException('Cannot parse artist token, possibly different image structure.', errorCode = PixivException.PARSE_TOKEN_DIFFERENT_IMAGE_STRUCTURE)
except TypeError:
raise PixivException('Cannot parse artist token, possibly no images.', errorCode = PixivException.PARSE_TOKEN_NO_IMAGES)
else :
temp = self.artistAvatar.split('/')
return temp[-2]
def process_sketch_post(caller, config, post_id):
config.loadConfig(path=caller.configfile)
br = PixivBrowserFactory.getBrowser()
msg = Fore.YELLOW + Style.NORMAL + f'Processing Post Id: {post_id}' + Style.RESET_ALL
PixivHelper.print_and_log(None, msg)
try:
post = br.sketch_get_post_by_post_id(post_id)
download_post(caller, config, post)
except Exception as ex:
if isinstance(ex, KeyboardInterrupt):
raise
caller.ERROR_CODE = getattr(ex, 'errorCode', -1)
exc_type, exc_value, exc_traceback = sys.exc_info()
traceback.print_exception(exc_type, exc_value, exc_traceback)
PixivHelper.print_and_log('error', f'Error at process_sketch_post(): {post_id}')
PixivHelper.print_and_log('error', f'Exception: {sys.exc_info()}')
def ParseBigImages(self, page, _br):
self.imageCount = 1
# Issue #224
# work manga
temp = page.find('a', attrs={'class': ' _work manga '})
if temp is not None:
if _br is None:
import PixivBrowserFactory
_br = PixivBrowserFactory.getExistingBrowser()
expected_url = '/member_illust.php?mode=big&illust_id=' + str(self.imageId)
try:
href = _br.fixUrl(expected_url)
print "Fetching big image page:", href
bigPage = _br.getPixivPage(url=href,
referer="https://www.pixiv.net/member_illust.php?mode=medium&illust_id=" + str(self.imageId))
bigImg = bigPage.find('img')
imgUrl = bigImg["src"]
# http://i2.pixiv.net/img-original/img/2013/12/27/01/51/37/40538869_p7.jpg
print "Found: ", imgUrl
bigImg.decompose()
bigPage.decompose()
del bigImg
del bigPage
return imgUrl
except Exception as ex:
print ex
# new layout for big 20141216
temp = page.find('img', attrs={'class': 'original-image'})
if temp is not None:
return str(temp['data-src'])
# new layout for big 20141212
temp = page.find('img', attrs={'class': 'big'})
if temp is not None:
return str(temp['data-src'])
# old layout
temp = page.find('img')['src']
return str(temp)
def ParseBigImages(self, page, _br):
self.imageCount = 1
# Issue #224
# work manga
temp = page.find('a', attrs={'class': ' _work manga '})
if temp is not None:
if _br is None:
import PixivBrowserFactory
_br = PixivBrowserFactory.getExistingBrowser()
expected_url = '/member_illust.php?mode=big&illust_id=' + str(self.imageId)
try:
href = _br.fixUrl(expected_url)
print "Fetching big image page:", href
bigPage = _br.getPixivPage(url=href,
referer="https://www.pixiv.net/member_illust.php?mode=medium&illust_id=" + str(self.imageId))
bigImg = bigPage.find('img')
imgUrl = bigImg["src"]
# http://i2.pixiv.net/img-original/img/2013/12/27/01/51/37/40538869_p7.jpg
print "Found: ", imgUrl
bigImg.decompose()
bigPage.decompose()
del bigImg
del bigPage
return imgUrl
except Exception as ex:
print ex
# new layout for big 20141216
temp = page.find('img', attrs={'class': 'original-image'})
if temp is not None:
return str(temp['data-src'])
# new layout for big 20141212
temp = page.find('img', attrs={'class': 'big'})
if temp is not None:
return str(temp['data-src'])
# old layout
temp = page.find('img')['src']
return str(temp)
def process_pixiv_by_fanbox_id(caller,
config,
artist_id,
start_page=1,
end_page=0,
tags=None,
title_prefix=""):
# Implement #1005
config.loadConfig(path=caller.configfile)
br = PixivBrowserFactory.getBrowser()
caller.set_console_title(title_prefix)
artist = br.fanboxGetArtistById(artist_id)
PixivArtistHandler.process_member(caller,
config,
artist.artistId,
user_dir='',
page=start_page,
end_page=end_page,
bookmark=False,
tags=tags,
title_prefix=title_prefix)
def process_fanbox_post(caller, config, post, artist):
# caller function/method
# TODO: ideally to be removed or passed as argument
db = caller.__dbManager__
br = PixivBrowserFactory.getBrowser()
db.insertPost(artist.artistId, post.imageId, post.imageTitle, post.feeRequired, post.worksDate, post.type)
post_files = []
flag_processed = False
if config.checkDBProcessHistory:
result = db.selectPostByPostId(post.imageId)
if result:
updated_date = result[5]
if updated_date is not None and post.updatedDateDatetime <= datetime_z.parse_datetime(updated_date):
flag_processed = True
try:
if not post.is_restricted and not flag_processed:
br.fanboxUpdatePost(post)
if ((not post.is_restricted) or config.downloadCoverWhenRestricted) and (not flag_processed) and config.downloadCover:
# cover image
if post.coverImageUrl is not None:
# fake the image_url for filename compatibility, add post id and pagenum
fake_image_url = post.coverImageUrl.replace("{0}/cover/".format(post.imageId),
"{0}_".format(post.imageId))
filename = PixivHelper.make_filename(config.filenameFormatFanboxCover,
post,
artistInfo=artist,
tagsSeparator=config.tagsSeparator,
tagsLimit=config.tagsLimit,
fileUrl=fake_image_url,
bookmark=None,
searchTags='',
useTranslatedTag=config.useTranslatedTag,
tagTranslationLocale=config.tagTranslationLocale)
filename = PixivHelper.sanitize_filename(filename, config.rootDirectory)
post.linkToFile[post.coverImageUrl] = filename
print("Downloading cover from {0}".format(post.coverImageUrl))
print("Saved to {0}".format(filename))
referer = "https://www.pixiv.net/fanbox/creator/{0}/post/{1}".format(artist.artistId, post.imageId)
# don't pass the post id and page number to skip db check
(result, filename) = PixivDownloadHandler.download_image(caller,
post.coverImageUrl,
filename,
referer,
config.overwrite,
config.retry,
config.backupOldFile,
image=post)
post_files.append((post.imageId, -1, filename))
PixivHelper.get_logger().debug("Download %s result: %s", filename, result)
else:
PixivHelper.print_and_log("info", "No Cover Image for post: {0}.".format(post.imageId))
if post.is_restricted:
PixivHelper.print_and_log("info", "Skipping post: {0} due to restricted post.".format(post.imageId))
return
if flag_processed:
PixivHelper.print_and_log("info", "Skipping post: {0} because it was downloaded before.".format(post.imageId))
return
if post.images is None or len(post.images) == 0:
PixivHelper.print_and_log("info", "No Image available in post: {0}.".format(post.imageId))
else:
current_page = 0
print("Image Count = {0}".format(len(post.images)))
for image_url in post.images:
# fake the image_url for filename compatibility, add post id and pagenum
fake_image_url = image_url.replace("{0}/".format(post.imageId),
"{0}_p{1}_".format(post.imageId, current_page))
filename = PixivHelper.make_filename(config.filenameFormatFanboxContent,
post,
artistInfo=artist,
tagsSeparator=config.tagsSeparator,
tagsLimit=config.tagsLimit,
fileUrl=fake_image_url,
bookmark=None,
searchTags='',
useTranslatedTag=config.useTranslatedTag,
tagTranslationLocale=config.tagTranslationLocale)
filename = PixivHelper.sanitize_filename(filename, config.rootDirectory)
post.linkToFile[image_url] = filename
referer = "https://www.pixiv.net/fanbox/creator/{0}/post/{1}".format(artist.artistId, post.imageId)
print("Downloading image {0} from {1}".format(current_page, image_url))
print("Saved to {0}".format(filename))
# filesize detection and overwrite issue
_oldvalue = config.alwaysCheckFileSize
config.alwaysCheckFileSize = False
# don't pass the post id and page number to skip db check
(result, filename) = PixivDownloadHandler.download_image(caller,
image_url,
filename,
referer,
False, # config.overwrite somehow unable to get remote filesize
config.retry,
config.backupOldFile,
image=post)
if result == PixivConstant.PIXIVUTIL_ABORTED:
raise KeyboardInterrupt()
post_files.append((post.imageId, current_page, filename))
PixivHelper.get_logger().debug("Download %s result: %s", filename, result)
config.alwaysCheckFileSize = _oldvalue
current_page = current_page + 1
# Implement #447
filename = PixivHelper.make_filename(config.filenameFormatFanboxInfo,
post,
artistInfo=artist,
tagsSeparator=config.tagsSeparator,
tagsLimit=config.tagsLimit,
fileUrl="{0}".format(post.imageId),
bookmark=None,
searchTags='',
useTranslatedTag=config.useTranslatedTag,
tagTranslationLocale=config.tagTranslationLocale)
filename = PixivHelper.sanitize_filename(filename, config.rootDirectory)
if config.writeImageInfo:
post.WriteInfo(filename + ".txt")
if config.writeHtml:
if post.type == "article" or (len(post.images) >= config.minImageCountForNonArticle and len(post.body_text) > config.minTextLengthForNonArticle):
html_template = PixivConstant.HTML_TEMPLATE
if os.path.isfile("template.html"):
reader = PixivHelper.open_text_file("template.html")
html_template = reader.read()
reader.close()
post.WriteHtml(html_template, config.useAbsolutePathsInHtml, filename + ".html")
if config.writeUrlInDescription:
PixivHelper.write_url_in_description(post, config.urlBlacklistRegex, config.urlDumpFilename)
finally:
if len(post_files) > 0:
db.insertPostImages(post_files)
db.updatePostUpdateDate(post.imageId, post.updatedDate)
def process_fanbox_artist_by_id(caller, config, artist_id, end_page, title_prefix=""):
config.loadConfig(path=caller.configfile)
br = PixivBrowserFactory.getBrowser()
caller.set_console_title(title_prefix)
try:
artist = br.fanboxGetArtistById(artist_id)
except PixivException as pex:
PixivHelper.print_and_log("error", f"Error getting FANBOX artist by id: {artist_id} ==> {pex.message}")
if pex.errorCode != PixivException.USER_ID_SUSPENDED:
return
artist = br.fanboxGetArtistById(artist_id, for_suspended=True)
formats = f"{config.filenameFormatFanboxCover}{config.filenameFormatFanboxContent}{config.filenameFormatFanboxInfo}"
name_flag = "%artist%" in formats
token_flag = "%member_token%" in formats
if name_flag or token_flag:
result = caller.__dbManager__.selectMemberByMemberId(artist.artistId)
if result:
artist.artistName = result[1]
artist.artistToken = result[7]
PixivHelper.print_and_log("info", f"Using saved artist name and token from db: {artist.artistName}, {artist.artistToken}")
else:
PixivHelper.print_and_log("warn", "Artist name or token found in FANBOX filename formats, but not in db.")
if name_flag:
artist.artistName = input(f"Please input %artist% for {artist_id}: ").strip()
if token_flag:
artist.artistToken = input(f"Please input %member_token% for {artist_id}: ").strip()
current_page = 1
next_url = None
image_count = 1
while True:
PixivHelper.print_and_log("info", "Processing {0}, page {1}".format(artist, current_page))
caller.set_console_title(f"{title_prefix} {artist}, page {current_page}")
try:
posts = br.fanboxGetPostsFromArtist(artist, next_url)
except PixivException as pex:
PixivHelper.print_and_log("error", "Error getting FANBOX posts of artist: {0} ==> {1}".format(artist, pex.message))
break
for post in posts:
print("#{0}".format(image_count))
post.printPost()
# images
if post.type in PixivModelFanbox.FanboxPost._supportedType:
try:
process_fanbox_post(caller, config, post, artist)
except KeyboardInterrupt:
choice = input("Keyboard Interrupt detected, continue to next post (Y/N)").rstrip("\r")
if choice.upper() == 'N':
PixivHelper.print_and_log("info", f"FANBOX artist: {artist}, processing aborted")
break
else:
continue
image_count += 1
PixivHelper.wait(config)
if not artist.hasNextPage:
PixivHelper.print_and_log("info", "No more post for {0}".format(artist))
break
current_page += 1
if 0 < end_page < current_page:
PixivHelper.print_and_log("info", "Reaching page limit for {0}, limit {1}".format(artist, end_page))
break
next_url = artist.nextUrl
if next_url is None:
PixivHelper.print_and_log("info", "No more next page for {0}".format(artist))
break
def process_tags(caller,
tags,
page=1,
end_page=0,
wild_card=True,
title_caption=False,
start_date=None,
end_date=None,
use_tags_as_dir=False,
member_id=None,
bookmark_count=None,
oldest_first=False,
type_mode=None,
notifier=None,
job_option=None):
# caller function/method
# TODO: ideally to be removed or passed as argument
config = caller.__config__
config.loadConfig(path=caller.configfile)
if notifier is None:
notifier = PixivHelper.dummy_notifier
# override the config source if job_option is give for filename formats
format_src = config
if job_option is not None:
format_src = job_option
search_page = None
_last_search_result = None
i = page
updated_limit_count = 0
try:
search_tags = PixivHelper.decode_tags(tags)
if use_tags_as_dir:
PixivHelper.print_and_log(None, "Save to each directory using query tags.")
format_src.rootDirectory += os.sep + PixivHelper.sanitize_filename(search_tags)
tags = PixivHelper.encode_tags(tags)
images = 1
last_image_id = -1
skipped_count = 0
use_bookmark_data = False
if bookmark_count is not None and bookmark_count > 0:
use_bookmark_data = True
offset = 60
start_offset = (page - 1) * offset
stop_offset = end_page * offset
PixivHelper.print_and_log('info', f'Searching for: ({search_tags}) {tags}')
flag = True
while flag:
(t, search_page) = PixivBrowserFactory.getBrowser().getSearchTagPage(tags,
i,
wild_card,
title_caption,
start_date,
end_date,
member_id,
oldest_first,
page,
use_bookmark_data,
bookmark_count,
type_mode,
r18mode=format_src.r18mode)
if len(t.itemList) == 0:
PixivHelper.print_and_log(None, 'No more images')
flag = False
elif _last_search_result is not None:
set1 = set((x.imageId) for x in _last_search_result.itemList)
difference = [x for x in t.itemList if (x.imageId) not in set1]
if len(difference) == 0:
PixivHelper.print_and_log(None, 'Getting duplicated result set, no more new images.')
flag = False
if flag:
for item in t.itemList:
last_image_id = item.imageId
PixivHelper.print_and_log(None, f'Image #{images}')
PixivHelper.print_and_log(None, f'Image Id: {item.imageId}')
if bookmark_count is not None and bookmark_count > item.bookmarkCount:
PixivHelper.print_and_log(None, f'Bookmark Count: {item.bookmarkCount}')
PixivHelper.print_and_log('info', f'Skipping imageId= {item.imageId} because less than bookmark count limit ({bookmark_count} > {item.bookmarkCount}).')
skipped_count = skipped_count + 1
continue
result = 0
while True:
try:
if t.availableImages > 0:
# PixivHelper.print_and_log(None, "Total Images: " + str(t.availableImages))
total_image = t.availableImages
if(stop_offset > 0 and stop_offset < total_image):
total_image = stop_offset
total_image = total_image - start_offset
# PixivHelper.print_and_log(None, "Total Images Offset: " + str(total_image))
else:
total_image = ((i - 1) * 20) + len(t.itemList)
title_prefix = "Tags:{0} Page:{1} Image {2}+{3} of {4}".format(tags, i, images, skipped_count, total_image)
if member_id is not None:
title_prefix = "MemberId: {0} Tags:{1} Page:{2} Image {3}+{4} of {5}".format(member_id,
tags,
i,
images,
skipped_count,
total_image)
result = PixivConstant.PIXIVUTIL_OK
if not caller.DEBUG_SKIP_PROCESS_IMAGE:
result = PixivImageHandler.process_image(caller,
config,
None,
item.imageId,
user_dir=format_src.rootDirectory,
search_tags=search_tags,
title_prefix=title_prefix,
bookmark_count=item.bookmarkCount,
image_response_count=item.imageResponse,
notifier=notifier,
job_option=job_option)
PixivHelper.wait(result, config)
break
except KeyboardInterrupt:
result = PixivConstant.PIXIVUTIL_KEYBOARD_INTERRUPT
break
except http.client.BadStatusLine:
PixivHelper.print_and_log(None, "Stuff happened, trying again after 2 second...")
time.sleep(2)
images = images + 1
if result in (PixivConstant.PIXIVUTIL_SKIP_DUPLICATE,
PixivConstant.PIXIVUTIL_SKIP_LOCAL_LARGER,
PixivConstant.PIXIVUTIL_SKIP_DUPLICATE_NO_WAIT):
updated_limit_count = updated_limit_count + 1
if config.checkUpdatedLimit != 0 and updated_limit_count >= config.checkUpdatedLimit:
PixivHelper.print_and_log(None, f"Skipping tags: {tags}")
PixivBrowserFactory.getBrowser().clear_history()
return
gc.collect()
continue
elif result == PixivConstant.PIXIVUTIL_KEYBOARD_INTERRUPT:
choice = input("Keyboard Interrupt detected, continue to next image (Y/N)").rstrip("\r")
if choice.upper() == 'N':
PixivHelper.print_and_log("info", f"Tags: {tags}, processing aborted.")
flag = False
break
else:
continue
PixivBrowserFactory.getBrowser().clear_history()
i = i + 1
_last_search_result = t
if end_page != 0 and end_page < i:
PixivHelper.print_and_log('info', f"End Page reached: {end_page}")
flag = False
if t.isLastPage:
PixivHelper.print_and_log('info', f"Last page: {i - 1}")
flag = False
if config.enableInfiniteLoop and i == 1001 and not oldest_first:
if last_image_id > 0:
# get the last date
PixivHelper.print_and_log('info', f"Hit page 1000, trying to get workdate for last image id: {last_image_id}.")
# referer = 'https://www.pixiv.net/en/artworks/{0}'.format(last_image_id)
result = PixivBrowserFactory.getBrowser().getImagePage(last_image_id)
_last_date = result[0].worksDateDateTime
# _start_date = image.worksDateDateTime + datetime.timedelta(365)
# hit the last page
i = 1
end_date = _last_date.strftime("%Y-%m-%d")
PixivHelper.print_and_log('info', f"Hit page 1000, looping back to page 1 with ecd: {end_date}.")
flag = True
last_image_id = -1
else:
PixivHelper.print_and_log('info', "No more image in the list.")
flag = False
PixivHelper.print_and_log(None, 'done')
if search_page is not None:
del search_page
except KeyboardInterrupt:
raise
except BaseException:
PixivHelper.print_and_log('error', f'Error at process_tags() at page {i}: {sys.exc_info()}')
try:
if search_page is not None:
dump_filename = f'Error page for search tags {tags} at page {i}.html'
PixivHelper.dump_html(dump_filename, search_page)
PixivHelper.print_and_log('error', f"Dumping html to: {dump_filename}")
except BaseException:
PixivHelper.print_and_log('error', f'Cannot dump page for search tags: {search_tags}')
raise
# -*- coding: UTF-8 -*-
import PixivUtil2
import PixivBrowserFactory
import PixivConfig
import getpass
import mechanize
__config__ = PixivConfig.PixivConfig()
PixivUtil2.__config__ = __config__
__config__.loadConfig()
__br__ = PixivUtil2.__br__ = PixivBrowserFactory.getBrowser(config=__config__)
def prepare():
## Log in
username = __config__.username
if username == '':
username = raw_input('Username ? ')
password = __config__.password
if password == '':
password = getpass.getpass('Password ? ')
result = False
if len(__config__.cookie) > 0:
result = __br__.loginUsingCookie(__config__.cookie)
if not result:
result = __br__.login(username, password)
return result
# -*- coding: UTF-8 -*-
import PixivUtil2
import PixivBrowserFactory
import PixivConfig
import getpass
import mechanize
__config__ = PixivConfig.PixivConfig()
PixivUtil2.__config__ = __config__
__config__.loadConfig()
__br__ = PixivUtil2.__br__ = PixivBrowserFactory.getBrowser(config=__config__)
def prepare():
## Log in
username = __config__.username
if username == '':
username = raw_input('Username ? ')
password = __config__.password
if password == '':
password = getpass.getpass('Password ? ')
result = False
if len(__config__.cookie) > 0:
result = __br__.loginUsingCookie(__config__.cookie)
if not result:
result = __br__.login(username, password)
return result
def ParseToken(self, page, fromImage=False):
if self.artistAvatar.endswith("no_profile.png"):
if fromImage:
temp = page.findAll(attrs={'class': 'works_display'})
token = str(temp[0].find('img')['src'])
return token.split('/')[-2]
else:
artistToken = None
try:
temp = page.find(attrs={
'class': 'display_works linkStyleWorks'
}).ul
if temp != None:
tokens = temp.findAll('img',
attrs={'class': '_thumbnail'})
for token in tokens:
try:
tempImage = token['data-src']
except:
tempImage = token['src']
folders = tempImage.split('/')
## skip http://i2.pixiv.net/img-inf/img/2013/04/07/03/08/21/34846113_s.jpg
if folders[3] == 'img-inf':
continue
artistToken = folders[-2]
if artistToken != 'common':
return artistToken
## all thumb images are using img-inf
## take the first image and check the medium page
if artistToken == None or artistToken != 'common':
PixivHelper.GetLogger().info(
"Unable to parse Artist Token from image list, try to parse from the first image"
)
import PixivBrowserFactory, PixivConstant
firstImageLink = temp.find('a',
attrs={'class':
'work'})['href']
if firstImageLink.find("http") != 0:
firstImageLink = PixivConstant.PIXIV_URL + firstImageLink
PixivHelper.GetLogger().info(
"Using: " + firstImageLink +
" for parsing artist token")
imagePage = PixivBrowserFactory.getBrowser().open(
firstImageLink)
imageResult = BeautifulSoup(imagePage.read())
token = str(
imageResult.find(attrs={
'class': 'works_display'
}).find('img')['src'])
return token.split('/')[-2]
raise PixivException(
'Cannot parse artist token, possibly different image structure.',
errorCode=PixivException.
PARSE_TOKEN_DIFFERENT_IMAGE_STRUCTURE)
except TypeError:
raise PixivException(
'Cannot parse artist token, possibly no images.',
errorCode=PixivException.PARSE_TOKEN_NO_IMAGES)
else:
temp = self.artistAvatar.split('/')
return temp[-2]
def process_tags(caller,
config,
tags,
page=1,
end_page=0,
wild_card=True,
title_caption=False,
start_date=None,
end_date=None,
use_tags_as_dir=False,
member_id=None,
bookmark_count=None,
sort_order='date_d',
type_mode=None,
notifier=None):
if notifier is None:
notifier = PixivHelper.dummy_notifier
search_page = None
_last_search_result = None
i = page
updated_limit_count = 0
empty_page_retry = 0
try:
search_tags = PixivHelper.decode_tags(tags)
root_dir = config.rootDirectory
if use_tags_as_dir:
PixivHelper.print_and_log(None, "Save to each directory using query tags.")
root_dir = config.rootDirectory + os.sep + PixivHelper.sanitize_filename(search_tags)
tags = PixivHelper.encode_tags(tags)
images = 1
last_image_id = -1
skipped_count = 0
use_bookmark_data = False
if bookmark_count is not None and bookmark_count > 0:
use_bookmark_data = True
offset = PixivTags.POSTS_PER_PAGE
start_offset = (page - 1) * offset
stop_offset = end_page * offset
PixivHelper.print_and_log('info', f'Searching for: ({search_tags}) {tags} with partial match = {wild_card} and title/caption = {title_caption}')
flag = True
while flag:
(t, search_page) = PixivBrowserFactory.getBrowser().getSearchTagPage(tags,
i,
wild_card=wild_card,
title_caption=title_caption,
start_date=start_date,
end_date=end_date,
member_id=member_id,
sort_order=sort_order,
start_page=page,
use_bookmark_data=use_bookmark_data,
bookmark_count=bookmark_count,
type_mode=type_mode,
r18mode=config.r18mode)
PixivHelper.print_and_log("info", f'Found {len(t.itemList)} images for page {i}.')
if len(t.itemList) == 0:
# Issue #1090
# check if the available images matching with current page * PixivTags.POSTS_PER_PAGE
# and wait for {timeout} seconds and retry the page up to {config.retry} times.
if _last_search_result is not None and _last_search_result.availableImages > (PixivTags.POSTS_PER_PAGE * i) and empty_page_retry < config.retry:
PixivHelper.print_and_log("warn", f'Server did not return images, expected to have more (Total Post = {_last_search_result.availableImages}, current max posts = {PixivTags.POSTS_PER_PAGE * i}).')
# wait at least 2 minutes before retry
delay = config.timeout
if delay < 120:
delay = 120
PixivHelper.print_and_log(None, f"Waiting for {delay} seconds before retrying.")
PixivHelper.print_delay(delay)
empty_page_retry = empty_page_retry + 1
PixivBrowserFactory.getBrowser().addheaders = [('User-agent', f'{config.useragent}{int(time.time())}')]
continue
else:
PixivHelper.print_and_log("warn", 'No more images.')
flag = False
elif _last_search_result is not None:
set1 = set((x.imageId) for x in _last_search_result.itemList)
difference = [x for x in t.itemList if (x.imageId) not in set1]
if len(difference) == 0:
PixivHelper.print_and_log("warn", 'Getting duplicated result set, no more new images.')
flag = False
if flag:
# Issue #1090 reset retry flag on succesfull load
empty_page_retry = 0
for item in t.itemList:
last_image_id = item.imageId
PixivHelper.print_and_log(None, f'Image #{images}')
PixivHelper.print_and_log(None, f'Image Id: {item.imageId}')
if bookmark_count is not None and bookmark_count > item.bookmarkCount:
PixivHelper.print_and_log(None, f'Bookmark Count: {item.bookmarkCount}')
PixivHelper.print_and_log('info', f'Skipping imageId= {item.imageId} because less than bookmark count limit ({bookmark_count} > {item.bookmarkCount}).')
skipped_count = skipped_count + 1
continue
result = 0
while True:
try:
if t.availableImages > 0:
# PixivHelper.print_and_log(None, "Total Images: " + str(t.availableImages))
total_image = t.availableImages
if(stop_offset > 0 and stop_offset < total_image):
total_image = stop_offset
total_image = total_image - start_offset
# PixivHelper.print_and_log(None, "Total Images Offset: " + str(total_image))
else:
total_image = ((i - 1) * 20) + len(t.itemList)
title_prefix = "Tags:{0} Page:{1} Image {2}+{3} of {4}".format(tags, i, images, skipped_count, total_image)
if member_id is not None:
title_prefix = "MemberId: {0} Tags:{1} Page:{2} Image {3}+{4} of {5}".format(member_id,
tags,
i,
images,
skipped_count,
total_image)
result = PixivConstant.PIXIVUTIL_OK
if not caller.DEBUG_SKIP_PROCESS_IMAGE:
result = PixivImageHandler.process_image(caller,
config,
None,
item.imageId,
user_dir=root_dir,
search_tags=search_tags,
title_prefix=title_prefix,
bookmark_count=item.bookmarkCount,
image_response_count=item.imageResponse,
notifier=notifier)
PixivHelper.wait(result, config)
break
except KeyboardInterrupt:
result = PixivConstant.PIXIVUTIL_KEYBOARD_INTERRUPT
break
except http.client.BadStatusLine:
PixivHelper.print_and_log(None, "Stuff happened, trying again after 2 second...")
PixivHelper.print_delay(2)
images = images + 1
if result in (PixivConstant.PIXIVUTIL_SKIP_DUPLICATE,
PixivConstant.PIXIVUTIL_SKIP_LOCAL_LARGER,
PixivConstant.PIXIVUTIL_SKIP_DUPLICATE_NO_WAIT):
updated_limit_count = updated_limit_count + 1
if config.checkUpdatedLimit != 0 and updated_limit_count >= config.checkUpdatedLimit:
PixivHelper.print_and_log(None, f"Skipping tags: {tags}")
PixivBrowserFactory.getBrowser().clear_history()
return
gc.collect()
continue
elif result == PixivConstant.PIXIVUTIL_KEYBOARD_INTERRUPT:
choice = input("Keyboard Interrupt detected, continue to next image (Y/N)").rstrip("\r")
if choice.upper() == 'N':
PixivHelper.print_and_log("info", f"Tags: {tags}, processing aborted.")
flag = False
break
else:
continue
PixivBrowserFactory.getBrowser().clear_history()
i = i + 1
_last_search_result = t
if end_page != 0 and end_page < i:
PixivHelper.print_and_log('info', f"End Page reached: {end_page}")
flag = False
if t.isLastPage:
PixivHelper.print_and_log('info', f"Last page: {i - 1}")
flag = False
if config.enableInfiniteLoop and i == 1001 and sort_order != 'date':
if last_image_id > 0:
# get the last date
PixivHelper.print_and_log('info', f"Hit page 1000, trying to get workdate for last image id: {last_image_id}.")
# referer = 'https://www.pixiv.net/en/artworks/{0}'.format(last_image_id)
result = PixivBrowserFactory.getBrowser().getImagePage(last_image_id)
_last_date = result[0].worksDateDateTime
# _start_date = image.worksDateDateTime + datetime.timedelta(365)
# hit the last page
i = 1
end_date = _last_date.strftime("%Y-%m-%d")
PixivHelper.print_and_log('info', f"Hit page 1000, looping back to page 1 with ecd: {end_date}.")
flag = True
last_image_id = -1
else:
PixivHelper.print_and_log('info', "No more image in the list.")
flag = False
PixivHelper.print_and_log(None, 'done')
if search_page is not None:
del search_page
except KeyboardInterrupt:
raise
except BaseException:
PixivHelper.print_and_log('error', f'Error at process_tags() at page {i}: {sys.exc_info()}')
try:
if search_page is not None:
dump_filename = f'Error page for search tags {tags} at page {i}.html'
PixivHelper.dump_html(dump_filename, search_page)
PixivHelper.print_and_log('error', f"Dumping html to: {dump_filename}")
except BaseException:
PixivHelper.print_and_log('error', f'Cannot dump page for search tags: {search_tags}')
raise
def process_member(caller,
config,
member_id,
user_dir='',
page=1,
end_page=0,
bookmark=False,
tags=None,
title_prefix="",
notifier=None,
job_option=None):
# caller function/method
# TODO: ideally to be removed or passed as argument
db = caller.__dbManager__
config.loadConfig(path=caller.configfile)
np = caller.np
np_is_valid = caller.np_is_valid
if notifier is None:
notifier = PixivHelper.dummy_notifier
# override the config source if job_option is give for filename formats
format_src = config
if job_option is not None:
format_src = job_option
list_page = None
msg = Fore.YELLOW + Style.BRIGHT + f'Processing Member Id: {member_id}' + Style.RESET_ALL
PixivHelper.print_and_log('info', msg)
notifier(type="MEMBER", message=msg)
if page != 1:
PixivHelper.print_and_log('info', 'Start Page: ' + str(page))
if end_page != 0:
PixivHelper.print_and_log('info', 'End Page: ' + str(end_page))
if config.numberOfPage != 0:
PixivHelper.print_and_log(
'info', 'Number of page setting will be ignored')
elif np != 0:
PixivHelper.print_and_log('info',
'End Page from command line: ' + str(np))
elif config.numberOfPage != 0:
PixivHelper.print_and_log(
'info', 'End Page from config: ' + str(config.numberOfPage))
# calculate the offset for display properties
offset = 48 # new offset for AJAX call
offset_start = (page - 1) * offset
offset_stop = end_page * offset
try:
no_of_images = 1
is_avatar_downloaded = False
flag = True
updated_limit_count = 0
image_id = -1
while flag:
PixivHelper.print_and_log(None, 'Page ', page)
caller.set_console_title(
f"{title_prefix}MemberId: {member_id} Page: {page}")
# Try to get the member page
while True:
try:
(artist, list_page
) = PixivBrowserFactory.getBrowser().getMemberPage(
member_id,
page,
bookmark,
tags,
r18mode=format_src.r18mode)
break
except PixivException as ex:
caller.ERROR_CODE = ex.errorCode
PixivHelper.print_and_log(
'info', f'Member ID ({member_id}): {ex}')
if ex.errorCode == PixivException.NO_IMAGES:
pass
else:
if list_page is None:
list_page = ex.htmlPage
if list_page is not None:
PixivHelper.dump_html(
f"Dump for {member_id} Error Code {ex.errorCode}.html",
list_page)
if ex.errorCode == PixivException.USER_ID_NOT_EXISTS or ex.errorCode == PixivException.USER_ID_SUSPENDED:
db.setIsDeletedFlagForMemberId(int(member_id))
PixivHelper.print_and_log(
'info',
f'Set IsDeleted for MemberId: {member_id} not exist.'
)
# db.deleteMemberByMemberId(member_id)
# PixivHelper.printAndLog('info', 'Deleting MemberId: ' + str(member_id) + ' not exist.')
if ex.errorCode == PixivException.OTHER_MEMBER_ERROR:
PixivHelper.print_and_log(None, ex.message)
caller.__errorList.append(
dict(type="Member",
id=str(member_id),
message=ex.message,
exception=ex))
return
except AttributeError:
# Possible layout changes, try to dump the file below
raise
except BaseException:
exc_type, exc_value, exc_traceback = sys.exc_info()
traceback.print_exception(exc_type, exc_value,
exc_traceback)
PixivHelper.print_and_log(
'error',
f'Error at processing Artist Info: {sys.exc_info()}')
PixivHelper.print_and_log(None,
f'Member Name : {artist.artistName}')
PixivHelper.print_and_log(None,
f'Member Avatar: {artist.artistAvatar}')
PixivHelper.print_and_log(None,
f'Member Token : {artist.artistToken}')
PixivHelper.print_and_log(
None, f'Member Background : {artist.artistBackground}')
print_offset_stop = offset_stop if offset_stop < artist.totalImages and offset_stop != 0 else artist.totalImages
PixivHelper.print_and_log(
None,
f'Processing images from {offset_start + 1} to {print_offset_stop} of {artist.totalImages}'
)
if not is_avatar_downloaded and config.downloadAvatar:
if user_dir == '':
target_dir = format_src.rootDirectory
else:
target_dir = user_dir
avatar_filename = PixivHelper.create_avatar_filename(
artist, target_dir, format_src)
if not caller.DEBUG_SKIP_PROCESS_IMAGE:
if artist.artistAvatar.find('no_profile') == -1:
PixivDownloadHandler.download_image(
caller,
artist.artistAvatar,
avatar_filename,
"https://www.pixiv.net/",
config.overwrite,
config.retry,
config.backupOldFile,
notifier=notifier)
# Issue #508
if artist.artistBackground is not None and artist.artistBackground.startswith(
"http"):
bg_name = PixivHelper.create_bg_filename_from_avatar_filename(
avatar_filename)
PixivDownloadHandler.download_image(
caller,
artist.artistBackground,
bg_name,
"https://www.pixiv.net/",
config.overwrite,
config.retry,
config.backupOldFile,
notifier=notifier)
is_avatar_downloaded = True
if config.autoAddMember:
db.insertNewMember(int(member_id))
db.updateMemberName(member_id, artist.artistName)
if not artist.haveImages:
PixivHelper.print_and_log('info',
f"No image found for: {member_id}")
db.updateLastDownloadDate(member_id)
flag = False
continue
result = PixivConstant.PIXIVUTIL_NOT_OK
for image_id in artist.imageList:
PixivHelper.print_and_log(None, f'#{no_of_images}')
retry_count = 0
while True:
try:
if artist.totalImages > 0:
# PixivHelper.safePrint("Total Images = " + str(artist.totalImages))
total_image_page_count = artist.totalImages
if (offset_stop > 0
and offset_stop < total_image_page_count):
total_image_page_count = offset_stop
total_image_page_count = total_image_page_count - offset_start
# PixivHelper.safePrint("Total Images Offset = " + str(total_image_page_count))
else:
total_image_page_count = (
(page - 1) * 20) + len(artist.imageList)
title_prefix_img = f"{title_prefix}MemberId: {member_id} Page: {page} Post {no_of_images}+{updated_limit_count} of {total_image_page_count}"
if not caller.DEBUG_SKIP_PROCESS_IMAGE:
result = PixivImageHandler.process_image(
caller,
config,
artist,
image_id,
user_dir,
bookmark,
title_prefix=title_prefix_img,
notifier=notifier,
job_option=job_option)
break
except KeyboardInterrupt:
result = PixivConstant.PIXIVUTIL_KEYBOARD_INTERRUPT
break
except BaseException:
if retry_count > config.retry:
PixivHelper.print_and_log(
'error', f"Giving up image_id: {image_id}")
return
retry_count = retry_count + 1
PixivHelper.print_and_log(
None,
f"Stuff happened, trying again after 2 second ({retry_count})"
)
exc_type, exc_value, exc_traceback = sys.exc_info()
traceback.print_exception(exc_type, exc_value,
exc_traceback)
PixivHelper.print_and_log(
"error",
f"Error at process_member(): {sys.exc_info()} Member Id: {member_id}"
)
time.sleep(2)
if result in (PixivConstant.PIXIVUTIL_SKIP_DUPLICATE,
PixivConstant.PIXIVUTIL_SKIP_LOCAL_LARGER,
PixivConstant.PIXIVUTIL_SKIP_DUPLICATE_NO_WAIT):
updated_limit_count = updated_limit_count + 1
if config.checkUpdatedLimit != 0 and updated_limit_count >= config.checkUpdatedLimit:
PixivHelper.safePrint(f"Skipping member: {member_id}")
db.updateLastDownloadDate(member_id)
PixivBrowserFactory.getBrowser(
config=config).clear_history()
return
gc.collect()
continue
if result == PixivConstant.PIXIVUTIL_KEYBOARD_INTERRUPT:
choice = input(
"Keyboard Interrupt detected, continue to next image (Y/N)"
).rstrip("\r")
if choice.upper() == 'N':
PixivHelper.print_and_log(
"info", f"Member: {member_id}, processing aborted")
flag = False
break
else:
continue
# return code from process image
if result == PixivConstant.PIXIVUTIL_SKIP_OLDER:
PixivHelper.print_and_log(
"info",
"Reached older images, skippin to next member.")
db.updateLastDownloadDate(member_id)
flag = False
break
no_of_images = no_of_images + 1
PixivHelper.wait(result, config)
if artist.isLastPage:
db.updateLastDownloadDate(member_id)
PixivHelper.print_and_log(None, "Last Page")
flag = False
page = page + 1
# page limit checking
if end_page > 0 and page > end_page:
PixivHelper.print_and_log(
None,
f"Page limit reached (from endPage limit ={end_page})")
db.updateLastDownloadDate(member_id)
flag = False
else:
if np_is_valid: # Yavos: overwriting config-data
if page > np and np > 0:
PixivHelper.print_and_log(
None,
f"Page limit reached (from command line ={np})")
flag = False
elif page > config.numberOfPage and config.numberOfPage > 0:
PixivHelper.print_and_log(
None,
f"Page limit reached (from config ={config.numberOfPage})"
)
flag = False
del artist
del list_page
PixivBrowserFactory.getBrowser(config=config).clear_history()
gc.collect()
log_message = ""
if int(image_id) > 0:
db.updateLastDownloadedImage(member_id, image_id)
log_message = f'last image_id: {image_id}'
else:
log_message = 'no images were found.'
PixivHelper.print_and_log(
"info", f"Member_id: {member_id} completed: {log_message}")
except KeyboardInterrupt:
raise
except Exception:
exc_type, exc_value, exc_traceback = sys.exc_info()
traceback.print_exception(exc_type, exc_value, exc_traceback)
PixivHelper.print_and_log(
'error', f'Error at process_member(): {sys.exc_info()}')
try:
if list_page is not None:
dump_filename = f'Error page for member {member_id} at page {page}.html'
PixivHelper.dump_html(dump_filename, list_page)
PixivHelper.print_and_log('error',
f"Dumping html to: {dump_filename}")
except BaseException:
PixivHelper.print_and_log(
'error', f'Cannot dump page for member_id: {member_id}')
raise
def process_image(caller,
config,
artist=None,
image_id=None,
user_dir='',
bookmark=False,
search_tags='',
title_prefix="",
bookmark_count=-1,
image_response_count=-1,
notifier=None,
job_option=None):
# caller function/method
# TODO: ideally to be removed or passed as argument
db = caller.__dbManager__
if notifier is None:
notifier = PixivHelper.dummy_notifier
# override the config source if job_option is give for filename formats
format_src = config
if job_option is not None:
format_src = job_option
parse_medium_page = None
image = None
result = None
referer = f'https://www.pixiv.net/artworks/{image_id}'
filename = f'no-filename-{image_id}.tmp'
try:
msg = Fore.YELLOW + Style.NORMAL + f'Processing Image Id: {image_id}' + Style.RESET_ALL
PixivHelper.print_and_log(None, msg)
notifier(type="IMAGE", message=msg)
# check if already downloaded. images won't be downloaded twice - needed in process_image to catch any download
r = db.selectImageByImageId(image_id, cols='save_name')
exists = False
in_db = False
if r is not None:
exists = db.cleanupFileExists(r[0])
in_db = True
# skip if already recorded in db and alwaysCheckFileSize is disabled and overwrite is disabled.
if in_db and not config.alwaysCheckFileSize and not config.overwrite:
PixivHelper.print_and_log(None, f'Already downloaded in DB: {image_id}')
gc.collect()
return PixivConstant.PIXIVUTIL_SKIP_DUPLICATE_NO_WAIT
# get the medium page
try:
(image, parse_medium_page) = PixivBrowserFactory.getBrowser().getImagePage(image_id=image_id,
parent=artist,
from_bookmark=bookmark,
bookmark_count=bookmark_count)
if len(title_prefix) > 0:
caller.set_console_title(f"{title_prefix} ImageId: {image.imageId}")
else:
caller.set_console_title(f"MemberId: {image.artist.artistId} ImageId: {image.imageId}")
except PixivException as ex:
caller.ERROR_CODE = ex.errorCode
caller.__errorList.append(dict(type="Image", id=str(image_id), message=ex.message, exception=ex))
if ex.errorCode == PixivException.UNKNOWN_IMAGE_ERROR:
PixivHelper.print_and_log('error', ex.message)
elif ex.errorCode == PixivException.SERVER_ERROR:
PixivHelper.print_and_log('error', f'Giving up image_id (medium): {image_id}')
elif ex.errorCode > 2000:
PixivHelper.print_and_log('error', f'Image Error for {image_id}: {ex.message}')
if parse_medium_page is not None:
dump_filename = f'Error medium page for image {image_id}.html'
PixivHelper.dump_html(dump_filename, parse_medium_page)
PixivHelper.print_and_log('error', f'Dumping html to: {dump_filename}')
else:
PixivHelper.print_and_log('error', f'Image ID ({image_id}): {ex}')
PixivHelper.print_and_log('error', f'Stack Trace: {sys.exc_info()}')
return PixivConstant.PIXIVUTIL_NOT_OK
except Exception as ex:
PixivHelper.print_and_log('error', f'Image ID ({image_id}): {ex}')
if parse_medium_page is not None:
dump_filename = f'Error medium page for image {image_id}.html'
PixivHelper.dump_html(dump_filename, parse_medium_page)
PixivHelper.print_and_log('error', f'Dumping html to: {dump_filename}')
PixivHelper.print_and_log('error', f'Stack Trace: {sys.exc_info()}')
exc_type, exc_value, exc_traceback = sys.exc_info()
traceback.print_exception(exc_type, exc_value, exc_traceback)
return PixivConstant.PIXIVUTIL_NOT_OK
download_image_flag = True
# date validation and blacklist tag validation
if config.dateDiff > 0:
if image.worksDateDateTime != datetime.datetime.fromordinal(1).replace(tzinfo=datetime_z.utc):
if image.worksDateDateTime < (datetime.datetime.today() - datetime.timedelta(config.dateDiff)).replace(tzinfo=datetime_z.utc):
PixivHelper.print_and_log('info', f'Skipping image_id: {image_id} because contains older than: {config.dateDiff} day(s).')
download_image_flag = False
result = PixivConstant.PIXIVUTIL_SKIP_OLDER
if config.useBlacklistMembers and download_image_flag:
if str(image.originalArtist.artistId) in caller.__blacklistMembers:
PixivHelper.print_and_log('info', f'Skipping image_id: {image_id} because contains blacklisted member id: {image.originalArtist.artistId}')
download_image_flag = False
result = PixivConstant.PIXIVUTIL_SKIP_BLACKLIST
if config.useBlacklistTags and download_image_flag:
for item in caller.__blacklistTags:
if item in image.imageTags:
PixivHelper.print_and_log('info', f'Skipping image_id: {image_id} because contains blacklisted tags: {item}')
download_image_flag = False
result = PixivConstant.PIXIVUTIL_SKIP_BLACKLIST
break
if config.useBlacklistTitles and download_image_flag:
for item in caller.__blacklistTitles:
if item in image.imageTitle:
PixivHelper.print_and_log('info', f'Skipping image_id: {image_id} because contains blacklisted Title: {item}')
download_image_flag = False
result = PixivConstant.PIXIVUTIL_SKIP_BLACKLIST
break
if download_image_flag and not caller.DEBUG_SKIP_DOWNLOAD_IMAGE:
if artist is None:
PixivHelper.print_and_log(None, f'Member Name : {image.artist.artistName}')
PixivHelper.print_and_log(None, f'Member Avatar: {image.artist.artistAvatar}')
PixivHelper.print_and_log(None, f'Member Token : {image.artist.artistToken}')
PixivHelper.print_and_log(None, f'Member Background : {image.artist.artistBackground}')
PixivHelper.print_and_log(None, f"Title: {image.imageTitle}")
tags_str = ', '.join(image.imageTags)
PixivHelper.print_and_log(None, f"Tags : {tags_str}")
PixivHelper.print_and_log(None, f"Date : {image.worksDateDateTime}")
PixivHelper.print_and_log(None, f"Mode : {image.imageMode}")
# get bookmark count
if ("%bookmark_count%" in format_src.filenameFormat or "%image_response_count%" in format_src.filenameFormat) and image.bookmark_count == -1:
PixivHelper.print_and_log(None, "Parsing bookmark page", end=' ')
bookmark_url = f'https://www.pixiv.net/bookmark_detail.php?illust_id={image_id}'
parse_bookmark_page = PixivBrowserFactory.getBrowser().getPixivPage(bookmark_url)
image.ParseBookmarkDetails(parse_bookmark_page)
parse_bookmark_page.decompose()
del parse_bookmark_page
PixivHelper.print_and_log(None, f"Bookmark Count : {image.bookmark_count}")
caller.__br__.back()
if config.useSuppressTags:
for item in caller.__suppressTags:
if item in image.imageTags:
image.imageTags.remove(item)
# get manga page
if image.imageMode == 'manga':
PixivHelper.print_and_log(None, f"Page Count : {image.imageCount}")
if user_dir == '': # Yavos: use config-options
target_dir = format_src.rootDirectory
else: # Yavos: use filename from list
target_dir = user_dir
result = PixivConstant.PIXIVUTIL_OK
manga_files = list()
page = 0
# Issue #639
source_urls = image.imageUrls
if config.downloadResized:
source_urls = image.imageResizedUrls
for img in source_urls:
PixivHelper.print_and_log(None, f'Image URL : {img}')
url = os.path.basename(img)
split_url = url.split('.')
if split_url[0].startswith(str(image_id)):
filename_format = format_src.filenameFormat
if image.imageMode == 'manga':
filename_format = format_src.filenameMangaFormat
filename = PixivHelper.make_filename(filename_format,
image,
tagsSeparator=config.tagsSeparator,
tagsLimit=config.tagsLimit,
fileUrl=url,
bookmark=bookmark,
searchTags=search_tags,
useTranslatedTag=config.useTranslatedTag,
tagTranslationLocale=config.tagTranslationLocale)
filename = PixivHelper.sanitize_filename(filename, target_dir)
if image.imageMode == 'manga' and config.createMangaDir:
manga_page = caller.__re_manga_page.findall(filename)
if len(manga_page) > 0:
splitted_filename = filename.split(manga_page[0][0], 1)
splitted_manga_page = manga_page[0][0].split("_p", 1)
# filename = splitted_filename[0] + splitted_manga_page[0] + os.sep + "_p" + splitted_manga_page[1] + splitted_filename[1]
filename = f"{splitted_filename[0]}{splitted_manga_page[0]}{os.sep}_p{splitted_manga_page[1]}{splitted_filename[1]}"
PixivHelper.print_and_log('info', f'Filename : {filename}')
result = PixivConstant.PIXIVUTIL_NOT_OK
try:
(result, filename) = PixivDownloadHandler.download_image(caller,
img,
filename,
referer,
config.overwrite,
config.retry,
config.backupOldFile,
image,
page,
notifier)
if result == PixivConstant.PIXIVUTIL_NOT_OK:
PixivHelper.print_and_log('error', f'Image url not found/failed to download: {image.imageId}')
elif result == PixivConstant.PIXIVUTIL_ABORTED:
raise KeyboardInterrupt()
manga_files.append((image_id, page, filename))
page = page + 1
except urllib.error.URLError:
PixivHelper.print_and_log('error', f'Error when download_image(), giving up url: {img}')
PixivHelper.print_and_log(None, '')
if config.writeImageInfo or config.writeImageJSON:
filename_info_format = format_src.filenameInfoFormat or format_src.filenameFormat
# Issue #575
if image.imageMode == 'manga':
filename_info_format = format_src.filenameMangaInfoFormat or format_src.filenameMangaFormat or filename_info_format
info_filename = PixivHelper.make_filename(filename_info_format,
image,
tagsSeparator=config.tagsSeparator,
tagsLimit=config.tagsLimit,
fileUrl=url,
appendExtension=False,
bookmark=bookmark,
searchTags=search_tags,
useTranslatedTag=config.useTranslatedTag,
tagTranslationLocale=config.tagTranslationLocale)
info_filename = PixivHelper.sanitize_filename(info_filename, target_dir)
# trim _pXXX
info_filename = re.sub(r'_p?\d+$', '', info_filename)
if config.writeImageInfo:
image.WriteInfo(info_filename + ".txt")
if config.writeImageJSON:
image.WriteJSON(info_filename + ".json")
if image.imageMode == 'ugoira_view':
if config.writeUgoiraInfo:
image.WriteUgoiraData(filename + ".js")
# Handle #451
if config.createUgoira and (result in (PixivConstant.PIXIVUTIL_OK, PixivConstant.PIXIVUTIL_SKIP_DUPLICATE)):
PixivDownloadHandler.handle_ugoira(image, filename, config, notifier)
if config.writeUrlInDescription:
PixivHelper.write_url_in_description(image, config.urlBlacklistRegex, config.urlDumpFilename)
if in_db and not exists:
result = PixivConstant.PIXIVUTIL_CHECK_DOWNLOAD # There was something in the database which had not been downloaded
# Only save to db if all images is downloaded completely
if result in (PixivConstant.PIXIVUTIL_OK,
PixivConstant.PIXIVUTIL_SKIP_DUPLICATE,
PixivConstant.PIXIVUTIL_SKIP_LOCAL_LARGER):
try:
db.insertImage(image.artist.artistId, image.imageId, image.imageMode)
except BaseException:
PixivHelper.print_and_log('error', f'Failed to insert image id:{image.imageId} to DB')
db.updateImage(image.imageId, image.imageTitle, filename, image.imageMode)
if len(manga_files) > 0:
db.insertMangaImages(manga_files)
# map back to PIXIVUTIL_OK (because of ugoira file check)
result = 0
if image is not None:
del image
if parse_medium_page is not None:
del parse_medium_page
gc.collect()
PixivHelper.print_and_log(None, '\n')
return result
except Exception as ex:
if isinstance(ex, KeyboardInterrupt):
raise
caller.ERROR_CODE = getattr(ex, 'errorCode', -1)
exc_type, exc_value, exc_traceback = sys.exc_info()
traceback.print_exception(exc_type, exc_value, exc_traceback)
PixivHelper.print_and_log('error', f'Error at process_image(): {image_id}')
PixivHelper.print_and_log('error', f'Exception: {sys.exc_info()}')
if parse_medium_page is not None:
dump_filename = f'Error medium page for image {image_id}.html'
PixivHelper.dump_html(dump_filename, parse_medium_page)
PixivHelper.print_and_log('error', f'Dumping html to: {dump_filename}')
raise
