lib.itmens/common/importers/douban.py

271 lines
12 KiB
Python
Raw Normal View History

add all NeoDB features to NiceDB (#115) * fix scraping failure with wepb image (merge upstream/fix-webp-scrape) * add filetype to requirements * add proxycrawl.com as fallback for douban scraper * load 3p js/css from cdn * add fix-cover task * fix book/album cover tasks * scrapestack * bandcamp scrape and preview ; manage.py scrape <url> ; make ^C work when DEBUG * use scrapestack when fix cover * add user agent to improve compatibility * search BandCamp for music albums * add missing MovieGenre * fix search 500 when song has no parent album * adjust timeout * individual scrapers * fix tmdb parser * export marks via rq; pref to send public toot; move import to data page * fix spotify import * fix edge cases * export: fix dupe tags * use rq to manage doufen import * add django command to manage rq jobs * fix export edge case * tune rq admin * fix detail page 502 step 1: async pull mastodon follow/block/mute list * fix detail page 502 step 2: calculate relationship by local cached data * manual sync mastodon follow info * domain_blocks parsing fix * marks by who i follows * adjust label * use username in urls * add page to list a user\'s review * review widget on user home page * fix preview 500 * fix typo * minor fix * fix google books parsing * allow mark/review visible to oneself * fix auto sync masto for new user * fix search 500 * add command to restart a sync task * reset visibility * delete user data * fix tag search result pagination * not upgrade to django 4 yet * basic doc * wip: collection * wip * wip * collection use htmx * show in-collection section for entities * fix typo * add su for easier debug * fix some 500s * fix login using alternative domain * hide data from disabled user * add item to list from detail page * my tags * collection: inline comment edit * show number of ratings * fix collection delete * more detail in collection view * use item template in search result * fix 500 * write index to meilisearch * fix search * reindex in batch * fix 500 * show search result from meilisearch * more search commands * index less fields * index new items only * search highlights * fix 500 * auto set search category * classic search if no meili server * fix index stats error * support typesense backend * workaround typesense bug * make external search async * fix 500, typo * fix cover scripts * fix minor issue in douban parser * supports m.douban.com and customized bandcamp domain * move account * reword with gender-friendly and instance-neutral language * Friendica does not have vapid_key in api response * enable anonymous search * tweak book result template * API v0 API v0 * fix meilisearch reindex * fix search by url error * login via twitter.com * login via pixelfed * minor fix * no refresh on inactive users * support refresh access token * get rid of /users/number-id/ * refresh twitter handler automatically * paste image when review * support PixelFed (very long token) * fix django-markdownx version * ignore single quote for meilisearch for now * update logo * show book review/mark from same isbn * show movie review/mark from same imdb * fix login with older mastodon servers * import Goodreads book list and profile * add timestamp to Goodreads import * support new google books api * import goodreads list * minor goodreads fix * click corner action icon to add to wishlist * clean up duplicated code * fix anonymous search * fix 500 * minor fix search 500 * show rating only if votes > 5 * Entity.refresh_rating() * preference to append text when sharing; clean up duplicated code * fix missing data for user tagged view * fix page link for tag view * fix 500 when language field longer than 10 * fix 500 when sharing mark for song * fix error when reimport goodread profile * fix minor typo * fix a rare 500 * error log dump less * fix tags in marks export * fix missing param in pagination * import douban review * clarify text * fix missing sheet in review import * review: show in progress * scrape douban: ignore unknown genre * minor fix * improve review import by guess entity urls * clear guide text for review import * improve review import form text * workaround some 500 * fix mark import error * fix img in review import * load external results earlier * ignore search server errors * simplify user register flow to avoid inconsistent state * Add a learn more link on login page * Update login.html * show mark created timestamp as mark time * no 500 for api error * redirect for expired tokens * ensure preference object created. * mark collections * tag list * fix tag display * fix sorting etc * fix 500 * fix potential export 500; save shared links * fix share to twittwe * fix review url * fix 500 * fix 500 * add timeline, etc * missing status change in timeline * missing id in timeline * timeline view by default * workaround bug in markdownx... * fix typo * option to create new collection when add from detail page * add missing announcement and tags in timeline home * add missing announcement * add missing announcement * opensearch * show fediverse shared link * public review no longer requires login * fix markdownx bug * fix 500 * use cloudflare cdn * validate jquery load and domain input * fix 500 * tips for goodreads import * collaborative collection * show timeline and profile link on nav bar * minor tweak * share collection * fix Goodreads search * show wish mark in timeline * resync failed urls with local proxy * resync failed urls with local proxy: check proxy first * scraper minor fix * resync failed urls * fix fields limit * fix douban parsing error * resync * scraper minor fix * scraper minor fix * scraper minor fix * local proxy * local proxy * sync default config from neodb * configurable site name * fix 500 * fix 500 for anonymous user * add sentry * add git version in log * add git version in log * no longer rely on cdnjs.cloudflare.com * move jq/cash to _common_libs template partial * fix rare js error * fix 500 * avoid double submission error * import tag in lower case * catch some js network errors * catch some js network errors * support more goodread urls * fix unaired tv in tmdb * support more google book urls * fix related series * more goodreads urls * robust googlebooks search * robust search * Update settings.py * Update scraper.py * Update requirements.txt * make nicedb work * doc update * simplify permission check * update doc * update doc for bug report link * skip spotify tracks * fix 500 * improve search api * blind fix import compatibility * show years for movie in timeline * show years for movie in timeline; thinner font * export reviews * revert user home to use jquery https://github.com/fabiospampinato/cash/issues/246 * IGDB * use IGDB for Steam * use TMDB for IMDb * steam: igdb then fallback to steam * keep change history * keep change history: add django settings * Steam: keep localized title/brief while merging IGDB * basic Docker support * rescrape * Create codeql-analysis.yml * Create SECURITY.md * Create pysa.yml Co-authored-by: doubaniux <goodsir@vivaldi.net> Co-authored-by: Your Name <you@example.com> Co-authored-by: Their Name <they@example.com> Co-authored-by: Mt. Front <mfcndw@gmail.com>
2022-11-09 13:56:50 -05:00
import openpyxl
import requests
import re
from lxml import html
from markdownify import markdownify as md
from datetime import datetime
from common.scraper import get_scraper_by_url
import logging
import pytz
from django.conf import settings
from django.core.exceptions import ObjectDoesNotExist
from user_messages import api as msg
import django_rq
from common.utils import GenerateDateUUIDMediaFilePath
import os
from books.models import BookReview, Book, BookMark, BookTag
from movies.models import MovieReview, Movie, MovieMark, MovieTag
from music.models import AlbumReview, Album, AlbumMark, AlbumTag
from games.models import GameReview, Game, GameMark, GameTag
from common.scraper import DoubanAlbumScraper, DoubanBookScraper, DoubanGameScraper, DoubanMovieScraper
from PIL import Image
from io import BytesIO
import filetype
from common.models import MarkStatusEnum
logger = logging.getLogger(__name__)
tz_sh = pytz.timezone('Asia/Shanghai')
def fetch_remote_image(url):
try:
print(f'fetching remote image {url}')
raw_img = None
ext = None
if settings.SCRAPESTACK_KEY is not None:
dl_url = f'http://api.scrapestack.com/scrape?access_key={settings.SCRAPESTACK_KEY}&url={url}'
elif settings.SCRAPERAPI_KEY is not None:
dl_url = f'http://api.scraperapi.com?api_key={settings.SCRAPERAPI_KEY}&url={url}'
else:
dl_url = url
img_response = requests.get(dl_url, timeout=settings.SCRAPING_TIMEOUT)
raw_img = img_response.content
img = Image.open(BytesIO(raw_img))
img.load() # corrupted image will trigger exception
content_type = img_response.headers.get('Content-Type')
ext = filetype.get_type(mime=content_type.partition(';')[0].strip()).extension
f = GenerateDateUUIDMediaFilePath(None, "x." + ext, settings.MARKDOWNX_MEDIA_PATH)
file = settings.MEDIA_ROOT + f
local_url = settings.MEDIA_URL + f
os.makedirs(os.path.dirname(file), exist_ok=True)
img.save(file)
# print(f'remote image saved as {local_url}')
return local_url
except Exception:
print(f'unable to fetch remote image {url}')
return url
class DoubanImporter:
total = 0
processed = 0
skipped = 0
imported = 0
failed = []
user = None
visibility = 0
file = None
def __init__(self, user, visibility):
self.user = user
self.visibility = visibility
def update_user_import_status(self, status):
self.user.preference.import_status['douban_pending'] = status
self.user.preference.import_status['douban_file'] = self.file
self.user.preference.import_status['douban_visibility'] = self.visibility
self.user.preference.import_status['douban_total'] = self.total
self.user.preference.import_status['douban_processed'] = self.processed
self.user.preference.import_status['douban_skipped'] = self.skipped
self.user.preference.import_status['douban_imported'] = self.imported
self.user.preference.import_status['douban_failed'] = self.failed
self.user.preference.save(update_fields=['import_status'])
def import_from_file(self, uploaded_file):
try:
wb = openpyxl.open(uploaded_file, read_only=True, data_only=True, keep_links=False)
wb.close()
file = settings.MEDIA_ROOT + GenerateDateUUIDMediaFilePath(None, "x.xlsx", settings.SYNC_FILE_PATH_ROOT)
os.makedirs(os.path.dirname(file), exist_ok=True)
with open(file, 'wb') as destination:
for chunk in uploaded_file.chunks():
destination.write(chunk)
self.file = file
self.update_user_import_status(2)
jid = f'Douban_{self.user.id}_{os.path.basename(self.file)}'
django_rq.get_queue('doufen').enqueue(self.import_from_file_task, job_id=jid)
except Exception:
return False
# self.import_from_file_task(file, user, visibility)
return True
mark_sheet_config = {
'想读': [MarkStatusEnum.WISH, DoubanBookScraper, Book, BookMark, BookTag],
'在读': [MarkStatusEnum.DO, DoubanBookScraper, Book, BookMark, BookTag],
'读过': [MarkStatusEnum.COLLECT, DoubanBookScraper, Book, BookMark, BookTag],
'想看': [MarkStatusEnum.WISH, DoubanMovieScraper, Movie, MovieMark, MovieTag],
'在看': [MarkStatusEnum.DO, DoubanMovieScraper, Movie, MovieMark, MovieTag],
'想看': [MarkStatusEnum.COLLECT, DoubanMovieScraper, Movie, MovieMark, MovieTag],
'想听': [MarkStatusEnum.WISH, DoubanAlbumScraper, Album, AlbumMark, AlbumTag],
'在听': [MarkStatusEnum.DO, DoubanAlbumScraper, Album, AlbumMark, AlbumTag],
'听过': [MarkStatusEnum.COLLECT, DoubanAlbumScraper, Album, AlbumMark, AlbumTag],
'想玩': [MarkStatusEnum.WISH, DoubanGameScraper, Game, GameMark, GameTag],
'在玩': [MarkStatusEnum.DO, DoubanGameScraper, Game, GameMark, GameTag],
'玩过': [MarkStatusEnum.COLLECT, DoubanGameScraper, Game, GameMark, GameTag],
}
review_sheet_config = {
'书评': [DoubanBookScraper, Book, BookReview],
'影评': [DoubanMovieScraper, Movie, MovieReview],
'乐评': [DoubanAlbumScraper, Album, AlbumReview],
'游戏评论&攻略': [DoubanGameScraper, Game, GameReview],
}
mark_data = {}
review_data = {}
entity_lookup = {}
def load_sheets(self):
f = open(self.file, 'rb')
wb = openpyxl.load_workbook(f, read_only=True, data_only=True, keep_links=False)
for data, config in [(self.mark_data, self.mark_sheet_config), (self.review_data, self.review_sheet_config)]:
for name in config:
data[name] = []
if name in wb:
print(f'{self.user} parsing {name}')
for row in wb[name].iter_rows(min_row=2, values_only=True):
cells = [cell for cell in row]
if len(cells) > 6:
data[name].append(cells)
for sheet in self.mark_data.values():
for cells in sheet:
# entity_lookup["title|rating"] = [(url, time), ...]
k = f'{cells[0]}|{cells[5]}'
v = (cells[3], cells[4])
if k in self.entity_lookup:
self.entity_lookup[k].append(v)
else:
self.entity_lookup[k] = [v]
self.total = sum(map(lambda a: len(a), self.review_data.values()))
def guess_entity_url(self, title, rating, timestamp):
k = f'{title}|{rating}'
if k not in self.entity_lookup:
return None
v = self.entity_lookup[k]
if len(v) > 1:
v.sort(key=lambda c: abs(timestamp - (datetime.strptime(c[1], "%Y-%m-%d %H:%M:%S") if type(c[1])==str else c[1]).replace(tzinfo=tz_sh)))
return v[0][0]
# for sheet in self.mark_data.values():
# for cells in sheet:
# if cells[0] == title and cells[5] == rating:
# return cells[3]
def import_from_file_task(self):
print(f'{self.user} import start')
msg.info(self.user, f'开始导入豆瓣评论')
self.update_user_import_status(1)
self.load_sheets()
print(f'{self.user} sheet loaded, {self.total} lines total')
self.update_user_import_status(1)
for name, param in self.review_sheet_config.items():
self.import_review_sheet(self.review_data[name], param[0], param[1], param[2])
self.update_user_import_status(0)
msg.success(self.user, f'豆瓣评论导入完成,共处理{self.total}篇,已存在{self.skipped}篇,新增{self.imported}篇。')
if len(self.failed):
msg.error(self.user, f'豆瓣评论导入时未能处理以下网址:\n{" , ".join(self.failed)}')
def import_review_sheet(self, worksheet, scraper, entity_class, review_class):
prefix = f'{self.user} |'
if worksheet is None: # or worksheet.max_row < 2:
print(f'{prefix} {review_class.__name__} empty sheet')
return
for cells in worksheet:
if len(cells) < 6:
continue
title = cells[0]
entity_title = re.sub('^《', '', re.sub('》$', '', cells[1]))
review_url = cells[2]
time = cells[3]
rating = cells[4]
content = cells[6]
self.processed += 1
if time:
if type(time) == str:
time = datetime.strptime(time, "%Y-%m-%d %H:%M:%S")
time = time.replace(tzinfo=tz_sh)
else:
time = None
if not content:
content = ""
if not title:
title = ""
r = self.import_review(entity_title, rating, title, review_url, content, time, scraper, entity_class, review_class)
if r == 1:
self.imported += 1
elif r == 2:
self.skipped += 1
else:
self.failed.append(review_url)
self.update_user_import_status(1)
def import_review(self, entity_title, rating, title, review_url, content, time, scraper, entity_class, review_class):
# return 1: done / 2: skipped / None: failed
prefix = f'{self.user} |'
url = self.guess_entity_url(entity_title, rating, time)
if url is None:
print(f'{prefix} fetching {review_url}')
try:
if settings.SCRAPESTACK_KEY is not None:
_review_url = f'http://api.scrapestack.com/scrape?access_key={settings.SCRAPESTACK_KEY}&url={review_url}'
else:
_review_url = review_url
r = requests.get(_review_url, timeout=settings.SCRAPING_TIMEOUT)
if r.status_code != 200:
print(f'{prefix} fetching error {review_url} {r.status_code}')
return
h = html.fromstring(r.content.decode('utf-8'))
for u in h.xpath("//header[@class='main-hd']/a/@href"):
if '.douban.com/subject/' in u:
url = u
if not url:
print(f'{prefix} fetching error {review_url} unable to locate entity url')
return
except Exception:
print(f'{prefix} fetching exception {review_url}')
return
try:
entity = entity_class.objects.get(source_url=url)
print(f'{prefix} matched {url}')
except ObjectDoesNotExist:
try:
print(f'{prefix} scraping {url}')
scraper.scrape(url)
form = scraper.save(request_user=self.user)
entity = form.instance
except Exception as e:
print(f"{prefix} scrape failed: {url} {e}")
logger.error(f"{prefix} scrape failed: {url}", exc_info=e)
return
params = {
'owner': self.user,
entity_class.__name__.lower(): entity
}
if review_class.objects.filter(**params).exists():
return 2
content = re.sub(r'<span style="font-weight: bold;">([^<]+)</span>', r'<b>\1</b>', content)
content = re.sub(r'(<img [^>]+>)', r'\1<br>', content)
content = re.sub(r'<div class="image-caption">([^<]+)</div>', r'<br><i>\1</i><br>', content)
content = md(content)
content = re.sub(r'(?<=!\[\]\()([^)]+)(?=\))', lambda x: fetch_remote_image(x[1]), content)
params = {
'owner': self.user,
'created_time': time,
'edited_time': time,
'title': title,
'content': content,
'visibility': self.visibility,
entity_class.__name__.lower(): entity,
}
review_class.objects.create(**params)
return 1