# -*- coding: utf-8 -*- # Copyright 2015-2018 Mike Fährmann # # This program is free software; you can redistribute it and/or modify # it under the terms of the GNU General Public License version 2 as # published by the Free Software Foundation. """Extract images from https://www.deviantart.com/""" from .common import Extractor, Message from .. import text, exception from ..cache import cache, memcache import itertools import mimetypes import datetime import time import math import re BASE_PATTERN = ( r"(?:https?://)?(?:" r"(?:www\.)?deviantart\.com/([\w-]+)|" r"([\w-]+)\.deviantart\.com)" ) class DeviantartExtractor(Extractor): """Base class for deviantart extractors""" category = "deviantart" directory_fmt = ["{category}", "{author[username]!l}"] filename_fmt = "{category}_{index}_{title}.{extension}" root = "https://www.deviantart.com" def __init__(self, match=None): Extractor.__init__(self) self.api = DeviantartAPI(self) self.offset = 0 self.flat = self.config("flat", True) self.original = self.config("original", True) self.user = match.group(1) or match.group(2) if match else None self.group = False self.commit_journal = { "html": self._commit_journal_html, "text": self._commit_journal_text, }.get(self.config("journals", "html")) def skip(self, num): self.offset += num return num def items(self): if self.user: self.group = not self.api.user_profile(self.user) if self.group: self.subcategory = "group-" + self.subcategory yield Message.Version, 1 for deviation in self.deviations(): if isinstance(deviation, tuple): url, data = deviation yield Message.Queue, url, data continue self.prepare(deviation) yield Message.Directory, deviation if "content" in deviation: content = deviation["content"] if self.original and deviation["is_downloadable"]: self._update_content(deviation, content) yield self.commit(deviation, content) if "videos" in deviation: video = max(deviation["videos"], key=lambda x: text.parse_int(x["quality"][:-1])) yield self.commit(deviation, video) if "flash" in deviation: yield self.commit(deviation, deviation["flash"]) if "excerpt" in deviation and self.commit_journal: journal = self.api.deviation_content(deviation["deviationid"]) yield self.commit_journal(deviation, journal) def deviations(self): """Return an iterable containing all relevant Deviation-objects""" return [] def prepare(self, deviation): """Adjust the contents of a Deviation-object""" try: deviation["index"] = deviation["url"].rpartition("-")[2] except KeyError: deviation["index"] = 0 if self.user: deviation["username"] = self.user deviation["da_category"] = deviation["category"] deviation["published_time"] = text.parse_int( deviation["published_time"]) @staticmethod def commit(deviation, target): url = target["src"] deviation["target"] = text.nameext_from_url(url, target.copy()) deviation["extension"] = deviation["target"]["extension"] return Message.Url, url, deviation def _commit_journal_html(self, deviation, journal): title = text.escape(deviation["title"]) url = deviation["url"] thumbs = deviation["thumbs"] html = journal["html"] date = datetime.datetime.utcfromtimestamp(deviation["published_time"]) shadow = SHADOW_TEMPLATE.format_map(thumbs[0]) if thumbs else "" if "css" in journal: css, cls = journal["css"], "withskin" else: css, cls = "", "journal-green" if html.find('
', 0, 250) != -1: needle = '
' header = HEADER_CUSTOM_TEMPLATE.format( title=title, url=url, date=str(date), ) else: needle = '
' catlist = deviation["category_path"].split("/") categories = " / ".join( ('{}' '').format(self.root, cpath, cat.capitalize()) for cat, cpath in zip( catlist, itertools.accumulate(catlist, lambda t, c: t + "/" + c) ) ) username = deviation["author"]["username"] urlname = deviation.get("username") or username.lower() header = HEADER_TEMPLATE.format( title=title, url=url, userurl="{}/{}/".format(self.root, urlname), username=username, date=date, categories=categories, ) html = JOURNAL_TEMPLATE_HTML.format( title=title, html=html.replace(needle, header, 1), shadow=shadow, css=css, cls=cls, ) deviation["extension"] = "htm" return Message.Url, html, deviation @staticmethod def _commit_journal_text(deviation, journal): date = datetime.datetime.utcfromtimestamp(deviation["published_time"]) content = "\n".join( text.unescape(text.remove_html(txt)) for txt in journal["html"].rpartition("") ) txt = JOURNAL_TEMPLATE_TEXT.format( title=deviation["title"], username=deviation["author"]["username"], date=date, content=content, ) deviation["extension"] = "txt" return Message.Url, txt, deviation @staticmethod def _find_folder(folders, name): pattern = r"[^\w]*" + name.replace("-", r"[^\w]+") + r"[^\w]*$" for folder in folders: if re.match(pattern, folder["name"]): return folder raise exception.NotFoundError("folder") def _folder_urls(self, folders, category): url = "{}/{}/{}/0/".format(self.root, self.user, category) return [(url + folder["name"], folder) for folder in folders] def _update_content(self, deviation, content): data = self.api.deviation_download(deviation["deviationid"]) if self.original == "images": url = data["src"].partition("?")[0] mtype = mimetypes.guess_type(url, False)[0] if not mtype or not mtype.startswith("image/"): return content.update(data) class DeviantartGalleryExtractor(DeviantartExtractor): """Extractor for all deviations from an artist's gallery""" subcategory = "gallery" archive_fmt = "g_{username}_{index}.{extension}" pattern = [BASE_PATTERN + r"(?:/(?:gallery/?(?:\?catpath=/)?)?)?$"] test = [ ("https://www.deviantart.com/shimoda7/gallery/", { "pattern": r"https://(s3.amazonaws.com/origin-(img|orig)" r".deviantart.net/|images-wixmp-\w+.wixmp.com/)", "count": ">= 30", "keyword": { "allows_comments": bool, "author": { "type": "regular", "usericon": str, "userid": "9AE51FC7-0278-806C-3FFF-F4961ABF9E2B", "username": "shimoda7", }, "category_path": str, "content": { "filesize": int, "height": int, "src": str, "transparency": bool, "width": int, }, "da_category": str, "deviationid": str, "?download_filesize": int, "extension": str, "index": str, "is_deleted": bool, "is_downloadable": bool, "is_favourited": bool, "is_mature": bool, "preview": { "height": int, "src": str, "transparency": bool, "width": int, }, "published_time": int, "stats": { "comments": int, "favourites": int, }, "target": dict, "thumbs": list, "title": str, "url": r"re:https://www.deviantart.com/shimoda7/art/[^/]+-\d+", "username": "shimoda7", }, }), ("https://www.deviantart.com/yakuzafc", { "pattern": r"https://www.deviantart.com/yakuzafc/gallery/0/", "count": ">= 15", }), ("https://www.deviantart.com/shimoda8/gallery/", { "exception": exception.NotFoundError, }), ("https://www.deviantart.com/shimoda7/gallery/?catpath=/", None), ("https://shimoda7.deviantart.com/gallery/", None), ("https://yakuzafc.deviantart.com/", None), ("https://shimoda7.deviantart.com/gallery/?catpath=/", None), ] def deviations(self): if self.flat and not self.group: return self.api.gallery_all(self.user, self.offset) else: folders = self.api.gallery_folders(self.user) return self._folder_urls(folders, "gallery") class DeviantartFolderExtractor(DeviantartExtractor): """Extractor for deviations inside an artist's gallery folder""" subcategory = "folder" directory_fmt = ["{category}", "{folder[owner]}", "{folder[title]}"] archive_fmt = "F_{folder[uuid]}_{index}.{extension}" pattern = [BASE_PATTERN + r"/gallery/(\d+)/([^/?&#]+)"] test = [ ("https://www.deviantart.com/shimoda7/gallery/722019/Miscellaneous", { "count": 5, "options": (("original", False),), }), ("https://www.deviantart.com/yakuzafc/gallery/37412168/Crafts", { "count": ">= 4", "options": (("original", False),), }), ("https://shimoda7.deviantart.com/gallery/722019/Miscellaneous", None), ("https://yakuzafc.deviantart.com/gallery/37412168/Crafts", None), ] def __init__(self, match): DeviantartExtractor.__init__(self, match) _, _, fid, self.fname = match.groups() self.folder = {"owner": self.user, "index": fid} def deviations(self): folders = self.api.gallery_folders(self.user) folder = self._find_folder(folders, self.fname) self.folder["title"] = folder["name"] self.folder["uuid"] = folder["folderid"] return self.api.gallery(self.user, folder["folderid"], self.offset) def prepare(self, deviation): DeviantartExtractor.prepare(self, deviation) deviation["folder"] = self.folder class DeviantartDeviationExtractor(DeviantartExtractor): """Extractor for single deviations""" subcategory = "deviation" archive_fmt = "{index}.{extension}" pattern = [BASE_PATTERN + r"/(?:art|journal)/[^/?&#]+-\d+"] test = [ (("https://www.deviantart.com/shimoda7/art/" "For-the-sake-of-a-memory-10073852"), { "content": "6a7c74dc823ebbd457bdd9b3c2838a6ee728091e", }), ("https://www.deviantart.com/zzz/art/zzz-1234567890", { "exception": exception.NotFoundError, }), (("https://www.deviantart.com/myria-moon/art/" "Aime-Moi-part-en-vadrouille-261986576"), { "pattern": (r"https?://s3\.amazonaws\.com/origin-orig\." r"deviantart\.net/a383/f/2013/135/e/7/[^.]+\.jpg\?"), }), (("https://shimoda7.deviantart.com/art/" "For-the-sake-of-a-memory-10073852"), None), ("https://zzz.deviantart.com/art/zzz-1234567890", None), (("https://myria-moon.deviantart.com/art/" "Aime-Moi-part-en-vadrouille-261986576"), None), ] def __init__(self, match): DeviantartExtractor.__init__(self, match) self.url = match.group(0) if not self.url.startswith("http"): self.url = "https://" + self.url def deviations(self): response = self.request(self.url, expect=range(400, 500)) deviation_id = text.extract(response.text, '//deviation/', '"')[0] if response.status_code >= 400 or not deviation_id: raise exception.NotFoundError("image") return (self.api.deviation(deviation_id),) class DeviantartStashExtractor(DeviantartDeviationExtractor): """Extractor for sta.sh-ed deviations""" subcategory = "stash" archive_fmt = "{index}.{extension}" pattern = [r"(?:https?://)?sta\.sh/()()[a-z0-9]+"] test = [ ("https://sta.sh/022c83odnaxc", { "pattern": r"https://s3.amazonaws.com/origin-orig.deviantart.net", "count": 1, }), ("https://sta.sh/21jf51j7pzl2", { "pattern": pattern[0], "count": 4, }), ("https://sta.sh/abcdefghijkl", { "exception": exception.HttpError, }), ] def deviations(self): page = self.request(self.url).text deviation_id = text.extract(page, '//deviation/', '"')[0] if deviation_id: yield self.api.deviation(deviation_id) else: page = text.extract( page, '