294 lines
9.0 KiB
XML
294 lines
9.0 KiB
XML
<?xml version="1.0" encoding="utf-8"?>
|
|
|
|
<!--
|
|
|
|
DON'T USE THIS PAGE FOR SCRAPING.
|
|
|
|
Seriously. You'll only get your IP blocked.
|
|
|
|
Download https://www.gutenberg.org/feeds/catalog.rdf.bz2 instead,
|
|
which contains *all* Project Gutenberg metadata in one RDF/XML file.
|
|
|
|
-->
|
|
|
|
<?python
|
|
import re
|
|
from libgutenberg import GutenbergGlobals as gg
|
|
|
|
if os.format == 'stanza':
|
|
os.type_opds = "application/atom+xml"
|
|
opds_relations = {
|
|
'cover': 'x-stanza-cover-image',
|
|
'thumb': 'x-stanza-cover-image-thumbnail',
|
|
}
|
|
else:
|
|
opds_relations = {
|
|
'new': 'http://opds-spec.org/sort/new',
|
|
'popular': 'http://opds-spec.org/sort/popular',
|
|
'cover': 'http://opds-spec.org/image',
|
|
'thumb': 'http://opds-spec.org/image/thumbnail',
|
|
'acquisition': 'http://opds-spec.org/acquisition',
|
|
}
|
|
|
|
?>
|
|
|
|
<feed xmlns="http://www.w3.org/2005/Atom"
|
|
xmlns:xi="http://www.w3.org/2001/XInclude"
|
|
xmlns:opds="http://opds-spec.org/2010/catalog"
|
|
xmlns:dcterms="http://purl.org/dc/terms/"
|
|
xmlns:opensearch="http://a9.com/-/spec/opensearch/1.1/"
|
|
xmlns:relevance="http://a9.com/-/opensearch/extensions/relevance/1.0/"
|
|
xmlns:py="http://genshi.edgewall.org/">
|
|
|
|
<id>${os.url_carry (host = os.host, start_index = os.start_index)}</id>
|
|
|
|
<updated>${os.now}</updated>
|
|
<title>${os.title}</title>
|
|
<subtitle>Free ebooks since 1971.</subtitle>
|
|
<author>
|
|
<name>Marcello Perathoner</name>
|
|
<uri>https://www.gutenberg.org</uri>
|
|
<email>webmaster@gutenberg.org</email>
|
|
</author>
|
|
<icon>${os.qualify ('/pics/favicon.png')}</icon>
|
|
|
|
<py:choose test="os.opensearch_support">
|
|
<py:when test="2">
|
|
<!--! fake opensearch support in Stanza and Aldiko -->
|
|
|
|
<!--! The next 2 links are for Stanza that can't read the standard opensearch description.
|
|
Stanza even requires unescaped '{' and '}' which are not valid characters in urls! AARGH!!
|
|
Aldiko needs fully qualified urls here!
|
|
-->
|
|
<link rel="search"
|
|
type="${os.type_opds}"
|
|
title="${os.placeholder}"
|
|
href="${os.add_amp (os.url ('search', host = os.host))}query={searchTerms}" />
|
|
<!--! routes would quote the invalid '{' and '}' -->
|
|
|
|
<link rel="x-stanza-search-suggestions"
|
|
type="application/x-suggestions+json"
|
|
href="${os.add_amp (os.url ('suggest', host = os.host, format = None))}query={searchTerms}" />
|
|
<!--! routes would quote '{' and '}' -->
|
|
</py:when>
|
|
|
|
<py:when test="1">
|
|
<!--! real opensearch support -->
|
|
|
|
<link rel="search"
|
|
type="application/opensearchdescription+xml"
|
|
title="Project Gutenberg Catalog Search"
|
|
href="${os.osd_url}" />
|
|
</py:when>
|
|
</py:choose>
|
|
|
|
<link rel="self"
|
|
title="This Page"
|
|
type="${os.type_opds}"
|
|
href="${os.url_carry (start_index = os.start_index)}" />
|
|
|
|
<link rel="alternate"
|
|
type="text/html"
|
|
title="HTML Page"
|
|
href="${os.url_carry (format = 'html', start_index = os.start_index)}" />
|
|
|
|
<link rel="start"
|
|
title="Start Page"
|
|
type="${os.type_opds}"
|
|
href="${os.url ('start')}" />
|
|
|
|
<link py:if="os.show_prev_page_link"
|
|
rel="first"
|
|
title="First Page"
|
|
type="${os.type_opds}"
|
|
href="${os.url_carry (start_index = 1)}" />
|
|
|
|
<link py:if="os.show_prev_page_link"
|
|
rel="previous"
|
|
title="Previous Page"
|
|
type="${os.type_opds}"
|
|
href="${os.url_carry (start_index = os.prev_page_index)}" />
|
|
|
|
<!--! Coolreader sucks up to 1000 entries without user paging. See:
|
|
http://crengine.git.sourceforge.net/git/gitweb.cgi?p=crengine/crengine;a=blob;f=android/src/org/coolreader/crengine/OPDSUtil.java
|
|
We give it one page. That's enough.
|
|
-->
|
|
|
|
<link py:if="os.show_next_page_link and not os.user_agent.startswith ('CoolReader/')"
|
|
rel="next"
|
|
title="Next Page"
|
|
type="${os.type_opds}"
|
|
href="${os.url_carry (start_index = os.next_page_index)}" />
|
|
|
|
<py:for each="e in os.entries">
|
|
<py:if test="isinstance (e, bs.Cat) and e.rel in opds_relations">
|
|
<link rel="${opds_relations[e.rel]}"
|
|
title="${e.title}"
|
|
type="${e.type or os.type_opds}"
|
|
href="${e.url}" />
|
|
</py:if>
|
|
</py:for>
|
|
|
|
<opensearch:itemsPerPage>${os.items_per_page}</opensearch:itemsPerPage>
|
|
<opensearch:startIndex>${os.start_index}</opensearch:startIndex>
|
|
|
|
<!--!
|
|
<opensearch:totalResults>${os.total_results}</opensearch:totalResults>
|
|
<opensearch:Query role="request"
|
|
searchTerms="${os.search_terms}"
|
|
startIndex="${os.start_index}" />
|
|
-->
|
|
|
|
<py:for each="e in os.entries">
|
|
|
|
<!--! Navigation feed entry -->
|
|
|
|
<py:if test="isinstance (e, bs.Cat)">
|
|
<py:choose>
|
|
<py:when test="e.rel == '__statusline__'" />
|
|
|
|
<py:otherwise>
|
|
<entry>
|
|
<updated>${os.now}</updated>
|
|
<id>${os.qualify (e.url)}</id>
|
|
<title>${e.title}</title>
|
|
<!--! according to spec type defaults to text but quickreader doesn't think so -->
|
|
<content py:if="e.subtitle or e.extra" type="text">${e.subtitle or e.extra}</content>
|
|
<category py:if="os.format == 'stanza' and e.header" label="${e.header}"
|
|
scheme="http://lexcycle.com/stanza/header" term="free" />
|
|
|
|
<link type="${e.type or os.type_opds}"
|
|
rel="${opds_relations.get (e.rel, 'subsection')}"
|
|
href='${e.url}' />
|
|
|
|
<py:for each="link in e.links">
|
|
<link type="${link.type}"
|
|
rel="${opds_relations.get (link.rel, 'subsection')}"
|
|
title="${link.title}"
|
|
length="${link.length}"
|
|
href="${link.url}" />
|
|
</py:for>
|
|
</entry>
|
|
</py:otherwise>
|
|
</py:choose>
|
|
</py:if>
|
|
|
|
<!--! Acquisition feed entry -->
|
|
|
|
<py:if test="isinstance (e, bs.DC)">
|
|
<entry>
|
|
<updated>${os.now}</updated>
|
|
<title>${re.sub (r'[\r\n].*', '', e.title)}</title>
|
|
|
|
<content type="xhtml">
|
|
<div xmlns="http://www.w3.org/1999/xhtml" >
|
|
<py:choose test="e.image_flags">
|
|
<p py:when="3">This edition has images.</p>
|
|
<p py:when="2">This edition had all images removed.</p>
|
|
</py:choose>
|
|
<py:for each="marc in e.marcs">
|
|
<py:choose test="">
|
|
<p py:when="marc.code[0]=='5'">
|
|
<?python
|
|
text = gg.xmlspecialchars (marc.text)
|
|
text = re.sub (r'(//\S+)', r'<a href="\1">\1</a>', text)
|
|
text = re.sub (r'#(\d+)',
|
|
r'<a href="/ebooks/\1.bibrec.mobile">#\1</a>', text)
|
|
?>
|
|
${marc.caption}:
|
|
${ Markup (gg.insert_breaks (text)) }
|
|
</p>
|
|
<p py:otherwise="">
|
|
${marc.caption}:
|
|
${ Markup (gg.insert_breaks (gg.xmlspecialchars (marc.text))) }
|
|
</p>
|
|
</py:choose>
|
|
</py:for>
|
|
<p py:for="author in e.authors">${author.role}: ${author.name_and_dates}</p>
|
|
<p>Ebook No.: ${e.project_gutenberg_id}</p>
|
|
<p>Published: ${e.hr_release_date}</p>
|
|
<p>Downloads: ${e.downloads}</p>
|
|
<p py:for="language in e.languages">Language: ${language.language}</p>
|
|
<p py:for="subject in e.subjects">Subject: ${subject.subject}</p>
|
|
<p py:for="locc in e.loccs">LoCC: ${locc.locc}</p>
|
|
<p py:for="category in e.categories">Category: ${category}</p>
|
|
<p>Rights: ${e.rights}</p>
|
|
</div>
|
|
</content>
|
|
|
|
<id>urn:gutenberg:${e.project_gutenberg_id}:${e.image_flags}</id>
|
|
<published>${e.xsd_release_date_time}</published>
|
|
<rights>${e.rights}</rights>
|
|
|
|
<py:for each="author in reversed (e.authors)">
|
|
<author py:if="author.marcrel in ('cre', 'aut')">
|
|
<name>${author.name}</name>
|
|
</author>
|
|
|
|
<contributor py:if="author.marcrel not in ('cre', 'aut')">
|
|
<name>${author.name}</name>
|
|
</contributor>
|
|
</py:for>
|
|
|
|
<category py:if="os.format == 'stanza' and e.header"
|
|
scheme="http://lexcycle.com/stanza/header"
|
|
term="free"
|
|
label="${e.header}" />
|
|
<category py:for="subject in e.subjects"
|
|
scheme="http://purl.org/dc/terms/LCSH"
|
|
term="${subject.subject}" />
|
|
<category py:for="locc in e.loccs"
|
|
scheme="http://purl.org/dc/terms/LCC"
|
|
term="${locc.id}"
|
|
label="${locc.locc}" />
|
|
<category py:for="category in e.categories"
|
|
scheme="http://purl.org/dc/terms/DCMIType"
|
|
term="$category" />
|
|
|
|
<dcterms:language py:for="language in e.languages">${language.id}</dcterms:language>
|
|
|
|
<py:for each="marc in e.marcs">
|
|
<dcterms:identifier py:if="marc.code == '010'">urn:lccn:${marc.text}</dcterms:identifier>
|
|
</py:for>
|
|
|
|
<relevance:score py:if="hasattr (e, 'score')">${e.score}</relevance:score>
|
|
|
|
<py:for each="link in e.links">
|
|
<link type="${link.type}"
|
|
rel="${opds_relations.get (link.rel, 'acquisition')}"
|
|
title="${link.title}"
|
|
length="${link.length}"
|
|
href="${link.url}" />
|
|
</py:for>
|
|
|
|
<link type="${os.type_opds}"
|
|
rel="related"
|
|
href="${os.url ('also', id = e.project_gutenberg_id)}"
|
|
title="Readers also downloaded…" />
|
|
|
|
<py:for each="author in e.authors">
|
|
<link type="${os.type_opds}"
|
|
rel="related"
|
|
href="${os.url ('author', id = author.id)}"
|
|
title="${_('By {author}').format (author = author.name)}…"/>
|
|
</py:for>
|
|
|
|
<py:for each="subject in e.subjects">
|
|
<link type="${os.type_opds}"
|
|
rel="related"
|
|
href="${os.url ('subject', id = subject.id)}"
|
|
title="${_('On {subject}').format (subject = subject.subject)}…"/>
|
|
</py:for>
|
|
|
|
<py:for each="bookshelf in e.bookshelves">
|
|
<link type="${os.type_opds}"
|
|
rel="related"
|
|
href="${os.url ('bookshelf', id = bookshelf.id)}"
|
|
title="${_('In {bookshelf}').format (bookshelf = bookshelf.bookshelf)}…"/>
|
|
</py:for>
|
|
</entry>
|
|
</py:if>
|
|
</py:for>
|
|
|
|
</feed>
|