{"id":123,"date":"2022-02-07T12:00:27","date_gmt":"2022-02-07T04:00:27","guid":{"rendered":"http:\/\/nas.hepcloud.top:7000\/?p=123"},"modified":"2022-11-01T23:50:22","modified_gmt":"2022-11-01T15:50:22","slug":"%e7%be%a4%e6%99%96nas%e6%95%99%e7%a8%8b%e5%8d%81%e4%b8%80%e3%80%81%e5%88%a9%e7%94%a8docker%e6%90%ad%e5%bb%ba%e4%b8%aa%e4%ba%ba%e5%9b%be%e4%b9%a6%e9%a6%86calibre-web","status":"publish","type":"post","link":"http:\/\/www.huerpu.cc:7000\/?p=123","title":{"rendered":"\u7fa4\u6656NAS docker\u7cfb\u5217\u6559\u7a0b(\u5341\u4e00)\u3001\u5229\u7528Docker\u642d\u5efa\u4e2a\u4eba\u56fe\u4e66\u9986(calibre-web)"},"content":{"rendered":"

\u7fa4\u6656NAS\u6559\u7a0b(\u5341\u4e00)\u3001\u5229\u7528Docker\u642d\u5efa\u4e2a\u4eba\u56fe\u4e66\u9986(calibre-web)<\/h3>\n

\u4e3a\u4e86\u66f4\u597d\u7684\u6d4f\u89c8\u4f53\u9a8c\uff0c\u6b22\u8fce\u5149\u987e\u52e4\u594b\u7684\u51ef\u5c14\u68ee\u540c\u5b66\u4e2a\u4eba\u535a\u5ba2http:\/\/www.huerpu.cc:7000<\/a><\/p>\n

\u4e2a\u4eba\u56fe\u4e66\u9986(calibre-web)\u662f\u8d85\u7ea7\u68d2\u7684\u4e00\u4e2a\u4e2a\u4eba\u56fe\u4e66\u9986\u8f6f\u4ef6\uff0c\u53ef\u4ee5\u50cf\u7fa4\u6656\u7684video station\u90a3\u6837\u4f7f\u7528\u6302\u5237\u5668\u6765\u7ba1\u7406\u548c\u89c2\u770b\u56fe\u4e66\uff0c\u7279\u522b\u68d2\u3002<\/p>\n

\u4e00\u3001\u4e0b\u8f7dcalibre-web\u955c\u50cf<\/h3>\n

\u5728\u7fa4\u6656docker\u5957\u4ef6\u4e2d\u641c\u7d22calibre\uff0c\u9009\u62e9\u7b2c\u4e8c\u4e2a\u4e0b\u8f7d\uff0c\u4e4b\u6240\u4ee5\u9009\u8fd9\u4e2a\uff0c\u662f\u56e0\u4e3a\u5b83\u62e5\u6709\u56fe\u4e66\u683c\u5f0f\u8f6c\u6362\u7684\u529f\u80fd\u3002<\/p>\n

\"197.png\"<\/p>\n

\u7136\u540e\u6162\u6162\u7b49\u5f85\u955c\u50cf\u4e0b\u8f7d\u597d\u3002<\/p>\n

\u4e8c\u3001\u914d\u7f6ecalibre\u542f\u52a8\u53c2\u6570<\/h3>\n

\u5728\u7fa4\u6656\u4e0a\u521b\u5efa\u6587\u4ef6\u5939config\u548cbooks\uff0c\u5206\u522b\u6302\u8f7d\u5230docker\u955c\u50cf\u7684\u78c1\u76d8\/calibre-web\/config\u548c\/books\uff0c\u4e0d\u6e05\u695a\u7684\u53ef\u4ee5\u770b\u955c\u50cf\u4ecb\u7ecd\uff0c\u5f88easy\u3002\u8fd9\u91cc\u5728\u7fa4\u6656\u521b\u5efa\u7684\u4e24\u4e2a\u6587\u4ef6\u5939\uff0c\u6743\u9650\u4e00\u5b9a\u8981\u7ed9\u8db3\uff0c\u8ba9\u4efb\u4f55\u4eba\u90fd\u53ef\u4ee5\u8bbf\u95ee\uff0c\u5982\u679c\u5728\u7fa4\u6656\u4e0a\u64cd\u4f5c\u4e0d\u65b9\u4fbf\uff0c\u53ef\u4ee5\u8003\u8651ssh\u8fde\u63a5\u7fa4\u6656\u4f7f\u7528chmod -R 777\u6765\u64cd\u4f5c\u3002<\/p>\n

\"197.png\"<\/p>\n

\u6620\u5c04\u7aef\u53e3\uff1a<\/p>\n

\"197.png\"<\/p>\n

\u5728\u542f\u52a8\u73af\u5883\u53d8\u91cf\u589e\u52a0\u4e24\u4e2aPUID\u548cPGID\uff0c\u8fd9\u4e2a\u6709\u70b9\u96be\u8bf4\u660e\u767d\uff0c\u5c31\u9ed8\u8ba4\u6309\u7167\u622a\u56fe\u5199\u5427\uff0c\u8868\u793a\u767b\u5f55admin\u7528\u6237\u7684\u6743\u9650\u3002<\/p>\n

\"197.png\"<\/p>\n

\u628a\u521d\u59cb\u5316\u7684metadata.db\u6587\u4ef6\u62f7\u8d1d\u5230\u4e0a\u9762\u6b65\u9aa4\u521b\u5efa\u7684config\u6587\u4ef6\u5939\u4e0b\uff0c\u6211\u7684\u662fe-book\/library\/config\u3002<\/p>\n

\u5982\u679c\u4e0d\u77e5\u9053metadata.db\u600e\u4e48\u83b7\u5f97\uff0c\u53ef\u4ee5\u5728win11\u4e0a\u5b89\u88c5calibre\uff0c\u5b89\u88c5\u8fc7\u7a0b\u4e2d\u4f1a\u63d0\u793a\u9009\u62e9\u4e66\u5e93\u7684\u76ee\u5f55\uff0c\u5c31\u5728\u8fd9\u4e2a\u4e0b\u9762\u3002<\/p>\n

\"197.png\"<\/p>\n

\"197.png\"<\/p>\n

\u5b89\u88c5\u597d\u542f\u52a8\u5373\u53ef\uff0c\u9ed8\u8ba4\u7528\u6237\u540d\u5bc6\u7801\u662f\uff1aadmin\/admin123\u3002<\/p>\n

\u6570\u636e\u5e93\u914d\u7f6e\uff0c\u5982\u679c\u4f60\u662f\u5b89\u88c5\u6211\u7684\u6b65\u9aa4\u9009\u7684\uff0c\u628ametadata.db\u590d\u5236\u5230\u4e86config\u76ee\u5f55\u4e0b\uff0c\u90a3\u4e48\u8fd9\u91cc\u586b\u5199\/calibre-web\/config\u5c31\u884c\u3002<\/p>\n

\"197.png\"<\/p>\n

\"197.png\"<\/p>\n

\u4e0b\u9762\u6211\u4eec\u7b80\u5355\u914d\u7f6e\u4e00\u4e0bcalibre\uff0c\u9009\u62e9\u53f3\u4e0a\u89d2\u7684\u8bbe\u7f6e\u6309\u94ae\uff0c\u7136\u540e\u9009\u529f\u80fd\u914d\u7f6e\uff0c\u628a\u542f\u7528\u4e0a\u4f20\u6253\u4e0a\u52fe\u3002<\/p>\n

\"197.png\"<\/p>\n

\"197.png\"<\/p>\n

\u4e09\u3001\u914d\u7f6e\u8c46\u74e3\u6302\u5237\u5668<\/h3>\n

\u5728\u7fa4\u6656docker\u5957\u4ef6\u4e2d\uff0c\u6253\u5f00calibre\u7684\u540e\u53f0\u547d\u4ee4\u7a97\u53e3\uff0c\u627e\u5230scholar.py\u6587\u4ef6\uff0c\u6211\u4eec\u5728\u540c\u76ee\u5f55\u4e0b\u589e\u91cf\u8c46\u74e3\u7684py\u6587\u4ef6\u3002<\/p>\n

\"197.png\"<\/p>\n

\u6267\u884c\u547d\u4ee4\u5982\u4e0b\uff1a<\/p>\n

#\u56de\u5230\u4e0a\u4e00\u7ea7\u76ee\u5f55\ncd ..\/\n# \u5bfb\u627escholar.py\u6587\u4ef6\nfind -name scholar.py\n# \u8fdb\u5165\u5230scholar.py\u6587\u4ef6\u6240\u5728\u8def\u5f84\ncd .\/app\/cps\/metadata_provider\/\n# \u65b0\u589e\u4e00\u4e2aNewdouban.py\u6587\u4ef6\nvi Newdouban.py<\/code><\/pre>\n
Newdouban.py\u5185\u5bb9\u5982\u4e0b\uff0c\u6587\u4ef6\u662f\u4ececalibre\u539f\u59cb\u955c\u50cf\u4ed3\u5e93\u62f7\u8d1d\u8fc7\u6765\u7684\uff1a<\/p>\n
import re\nimport time\n\nimport requests\nfrom concurrent.futures import ThreadPoolExecutor, as_completed\nfrom urllib.parse import urlparse, unquote\nfrom lxml import etree\nfrom functools import lru_cache\n\nfrom cps.services.Metadata import Metadata\n\nDOUBAN_SEARCH_JSON_URL = "https:\/\/www.douban.com\/j\/search"\nDOUBAN_BOOK_CAT = "1001"\nDOUBAN_BOOK_CACHE_SIZE = 500  # \u6700\u5927\u7f13\u5b58\u6570\u91cf\nDOUBAN_CONCURRENCY_SIZE = 5  # \u5e76\u53d1\u67e5\u8be2\u6570\nDEFAULT_HEADERS = {\n    'user-agent': 'Mozilla\/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit\/537.36 (KHTML, like Gecko) Chrome\/71.0.3573.0 Safari\/537.36'\n}\nPROVIDER_NAME = "New Douban Books"\nPROVIDER_ID = "new_douban"\n\nclass NewDouban(Metadata):\n    __name__ = PROVIDER_NAME\n    __id__ = PROVIDER_ID\n\n    def __init__(self):\n        self.searcher = DoubanBookSearcher()\n        super().__init__()\n\n    def search(self, query, generic_cover=""):\n        if self.active:\n            return self.searcher.search_books(query)\n\nclass DoubanBookSearcher:\n\n    def __init__(self):\n        self.book_loader = DoubanBookLoader()\n        self.thread_pool = ThreadPoolExecutor(max_workers=10, thread_name_prefix='douban_async')\n\n    def calc_url(self, href):\n        query = urlparse(href).query\n        params = {item.split('=')[0]: item.split('=')[1] for item in query.split('&')}\n        url = unquote(params['url'])\n        return url\n\n    def load_book_urls(self, query):\n        url = DOUBAN_SEARCH_JSON_URL\n        params = {"start": 0, "cat": DOUBAN_BOOK_CAT, "q": query}\n        res = requests.get(url, params, headers=DEFAULT_HEADERS)\n        book_urls = []\n        if res.status_code in [200, 201]:\n            book_list_content = res.json()\n            for item in book_list_content['items'][0:DOUBAN_CONCURRENCY_SIZE]:  # \u83b7\u53d6\u90e8\u5206\u6570\u636e\uff0c\u9ed8\u8ba45\u6761\n                html = etree.HTML(item)\n                a = html.xpath('\/\/a[@class="nbg"]')\n                if len(a):\n                    href = a[0].attrib['href']\n                    parsed = self.calc_url(href)\n                    book_urls.append(parsed)\n        return book_urls\n\n    def search_books(self, query):\n        book_urls = self.load_book_urls(query)\n        books = []\n        futures = [self.thread_pool.submit(self.book_loader.load_book, book_url) for book_url in book_urls]\n        for future in as_completed(futures):\n            book = future.result()\n            if book is not None:\n                books.append(future.result())\n        return books\n\nclass DoubanBookLoader:\n\n    def __init__(self):\n        self.book_parser = DoubanBookHtmlParser()\n\n    @lru_cache(maxsize=DOUBAN_BOOK_CACHE_SIZE)\n    def load_book(self, url):\n        book = None\n        start_time = time.time()\n        res = requests.get(url, headers=DEFAULT_HEADERS)\n        if res.status_code in [200, 201]:\n            print("\u4e0b\u8f7d\u4e66\u7c4d:{}\u6210\u529f,\u8017\u65f6{:.0f}ms".format(url, (time.time() - start_time) * 1000))\n            book_detail_content = res.content\n            book = self.book_parser.parse_book(url, book_detail_content.decode("utf8"))\n        return book\n\nclass DoubanBookHtmlParser:\n    def __init__(self):\n        self.id_pattern = re.compile(".*\/subject\/(\\\\d+)\/?")\n\n    def parse_book(self, url, book_content):\n        book = {}\n        html = etree.HTML(book_content)\n        title_element = html.xpath("\/\/span[@property='v:itemreviewed']")\n        book['title'] = self.get_text(title_element)\n        share_element = html.xpath("\/\/a[@data-url]")\n        if len(share_element):\n            url = share_element[0].attrib['data-url']\n        book['url'] = url\n        id_match = self.id_pattern.match(url)\n        if id_match:\n            book['id'] = id_match.group(1)\n        img_element = html.xpath("\/\/a[@class='nbg']")\n        if len(img_element):\n            cover = img_element[0].attrib['href']\n            if not cover or cover.endswith('update_image'):\n                book['cover'] = ''\n            else:\n                book['cover'] = cover\n        rating_element = html.xpath("\/\/strong[@property='v:average']")\n        book['rating'] = self.get_rating(rating_element)\n        elements = html.xpath("\/\/span[@class='pl']")\n        book['authors'] = []\n        book['publisher'] = ''\n        for element in elements:\n            text = self.get_text(element)\n            if text.startswith("\u4f5c\u8005"):\n                book['authors'].extend([self.get_text(author_element) for author_element in element.findall("..\/\/a")])\n            elif text.startswith("\u8bd1\u8005"):\n                book['authors'].extend([self.get_text(author_element) for author_element in element.findall("..\/\/a")])\n            elif text.startswith("\u51fa\u7248\u793e"):\n                book['publisher'] = self.get_tail(element)\n            elif text.startswith("\u51fa\u7248\u5e74"):\n                book['publishedDate'] = self.get_tail(element)\n            elif text.startswith("\u4e1b\u4e66"):\n                book['series'] = self.get_text(element.getnext())\n        summary_element = html.xpath("\/\/div[@id='link-report']\/\/div[@class='intro']")\n        book['description'] = ''\n        if len(summary_element):\n            book['description'] = etree.tostring(summary_element[-1], encoding="utf8").decode("utf8").strip()\n        tag_elements = html.xpath("\/\/a[contains(@class, 'tag')]")\n        if len(tag_elements):\n            book['tags'] = [tag_element.text.strip() for tag_element in tag_elements]\n        book['source'] = {\n            "id": PROVIDER_ID,\n            "description": PROVIDER_NAME,\n            "link": "https:\/\/book.douban.com\/"\n        }\n        return book\n\n    def get_rating(self, rating_element):\n        return float(self.get_text(rating_element, '0')) \/ 2\n\n    def get_text(self, element, default_str=''):\n        text = default_str\n        if len(element) and element[0].text:\n            text = element[0].text.strip()\n        elif isinstance(element, etree._Element) and element.text:\n            text = element.text.strip()\n        return text if text else default_str\n\n    def get_tail(self, element, default_str=''):\n        text = default_str\n        if isinstance(element, etree._Element) and element.tail:\n            text = element.tail.strip()\n        return text if text else default_str\n<\/code><\/pre>\n
\u539f\u6765\u65e7\u7684\u6587\u4ef6\u5e94\u8be5\u662fdouban.py\uff0c\u4f46\u73b0\u5728\u8c8c\u4f3c\u6709\u70b9\u5c0f\u95ee\u9898\uff1a<\/p>\n
import requests\n\nfrom cps.services.Metadata import Metadata\n\nclass Douban(Metadata):\n    __name__ = "Douban Books"\n    __id__ = "douban"\n    doubanUrl = "http:\/\/YOUR_NAS_IP:8085"\n    headers = {\n        'user-agent': 'Mozilla\/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit\/537.36 (KHTML, like Gecko) Chrome\/71.0.3573.0 Safari\/537.36'\n    }\n\n    def search(self, query, generic_cover=""):\n        if self.active:\n            val = list()\n            result = requests.get(self.doubanUrl + "\/v2\/book\/search?q=" + query.replace(" ", "+"), headers=self.headers)\n            for r in result.json()['books']:\n                v = dict()\n                v['id'] = r['id']\n                v['title'] = r['title']\n                v['authors'] = r.get('authors', [])\n                v['description'] = r.get('summary', "")\n                v['publisher'] = r.get('publisher', "")\n                v['publishedDate'] = r.get('pubdate', "")\n                v['tags'] = [tag.get('name', '') for tag in r.get('tags', [])]\n                rating = r['rating'].get('average', '0')\n                if not rating:\n                    rating = '0'\n                v['rating'] = float(rating) \/ 2\n                if r.get('image'):\n                    v['cover'] = r.get('image')\n                else:\n                    v['cover'] = generic_cover\n                v['source'] = {\n                    "id": self.__id__,\n                    "description": self.__name__,\n                    "link": "https:\/\/book.douban.com\/"\n                }\n                v['url'] = "https:\/\/book.douban.com\/subject\/" + r['id']\n                val.append(v)\n            return val\n<\/code><\/pre>\n
\u7136\u540e\u6309esc\uff0c\u8f93\u5165wq\u4fdd\u5b58\u9000\u51fa\uff0c\u91cd\u542f\u5bb9\u5668\u3002<\/p>\n
\u8fd9\u4e2a\u65f6\u5019\u5c31\u53ef\u4ee5\u770b\u5230\u6211\u4eec\u589e\u52a0\u7684\u8c46\u74e3\u7684\u6302\u5237\u5668\u4e86\uff0c\u56e0\u4e3a\u6211\u662f\u5f04\u597d\u4e4b\u540e\u622a\u7684\u56fe\uff0c\u6240\u4ee5\u56fe\u7247\u662f\u6709\u56fe\u4e66\u5c01\u9762\u7684\uff1a<\/p>\n
\"197.png\"<\/p>\n
\"197.png\"<\/p>\n
\"197.png\"<\/p>\n
\u56db\u3001\u8def\u7531\u5668\u8bbe\u7f6ecalibre\u7684\u7aef\u53e3\u8f6c\u53d1\u5230\u5916\u7f51<\/h3>\n\n\n\n\n\n
\u540d\u79f0<\/th>\n\u534f\u8bae<\/th>\n\u5916\u90e8\u7aef\u53e3<\/th>\n\u5185\u90e8IP\u5730\u5740<\/th>\n\u5185\u90e8\u7aef\u53e3<\/th>\n<\/tr>\n<\/thead>\n
library-calibre<\/td>\nTCP<\/td>\n8089<\/td>\n192.168.31.19<\/td>\n8089<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n
\u540d\u79f0\u53ef\u4ee5\u968f\u4fbf\u586b\uff0c\u534f\u8bae\u9009\u62e9TCP\uff0c\u5916\u90e8\u7aef\u53e3\u662f\u5916\u7f51\u8bbf\u95ee\u7684\u7aef\u53e3\uff0c\u5185\u90e8IP\u5730\u5740\u662f\u7fa4\u6656\u7684\u672c\u5730IP\uff0c\u5185\u90e8\u7aef\u53e3\u662f\u5bb9\u5668\u66b4\u9732\u7ed9\u5bbf\u4e3b\u673a\u7684\u7aef\u53e3\u53f7\uff0c\u4e3a\u4e86\u65b9\u4fbf\u6211\u4eec\u5168\u90e8\u8bbe\u7f6e\u6210\u4e86\u7edf\u4e00\u76848089\u3002<\/p>\n
\u7136\u540e\u5c31\u53ef\u4ee5\u6109\u5feb\u7684\u5916\u7f51\u8bbf\u95ee\u4e86\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"
\u7fa4\u6656NAS\u6559\u7a0b(\u5341\u4e00)\u3001\u5229\u7528Docker\u642d\u5efa\u4e2a\u4eba\u56fe\u4e66\u9986(calibre-web) \u4e3a\u4e86\u66f4\u597d\u7684\u6d4f\u89c8\u4f53\u9a8c\uff0c\u6b22\u8fce\u5149\u987e […]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[4,10],"tags":[],"class_list":["post-123","post","type-post","status-publish","format-standard","hentry","category-nas","category-nas-docker"],"_links":{"self":[{"href":"http:\/\/www.huerpu.cc:7000\/index.php?rest_route=\/wp\/v2\/posts\/123","targetHints":{"allow":["GET"]}}],"collection":[{"href":"http:\/\/www.huerpu.cc:7000\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"http:\/\/www.huerpu.cc:7000\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"http:\/\/www.huerpu.cc:7000\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"http:\/\/www.huerpu.cc:7000\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=123"}],"version-history":[{"count":1,"href":"http:\/\/www.huerpu.cc:7000\/index.php?rest_route=\/wp\/v2\/posts\/123\/revisions"}],"predecessor-version":[{"id":521,"href":"http:\/\/www.huerpu.cc:7000\/index.php?rest_route=\/wp\/v2\/posts\/123\/revisions\/521"}],"wp:attachment":[{"href":"http:\/\/www.huerpu.cc:7000\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=123"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"http:\/\/www.huerpu.cc:7000\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=123"},{"taxonomy":"post_tag","embeddable":true,"href":"http:\/\/www.huerpu.cc:7000\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=123"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}