Benature/omnivore
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Merge pull request #2411 from omnivore-app/fix/readability-missing-links

Browse Source 
fix: links removed
This commit is contained in:
Hongbo Wu
2023-06-26 16:56:47 +08:00
committed by GitHub
parent d954f44933 e446634504
commit 6d3989e04a
14 changed files with 3587 additions and 472 deletions
Download Patch File Download Diff File Expand all files Collapse all files

63
packages/puppeteer-parse/index.js
View File

@ -326,16 +326,16 @@ const sendImportStatusUpdate = async (userId, taskId, status) => {
async function fetchContent(req, res) {
let functionStartTime = Date.now();
let url = getUrl(req);
const userId = (req.query ? req.query.userId : undefined) || (req.body ? req.body.userId : undefined);
const articleSavingRequestId = (req.query ? req.query.saveRequestId : undefined) || (req.body ? req.body.saveRequestId : undefined);
const state = req.body.state
const labels = req.body.labels
const source = req.body.source || 'parseContent';
const taskId = req.body.taskId; // taskId is used to update import status
const urlStr = (req.query ? req.query.url : undefined) || (req.body ? req.body.url : undefined);
let logRecord = {
url,
url: urlStr,
userId,
articleSavingRequestId,
labels: {
@ -348,30 +348,31 @@ async function fetchContent(req, res) {
console.info(`Article parsing request`, logRecord);
if (!url) {
logRecord.urlIsInvalid = true;
console.info(`Valid URL to parse not specified`, logRecord);
return res.sendStatus(400);
}
// pre handle url with custom handlers
let title, content, contentType, importStatus;
let url, context, page, finalUrl, title, content, contentType, importStatus, statusCode = 200;
try {
const browser = await getBrowserPromise;
const result = await preHandleContent(url, browser);
if (result && result.url) {
url = result.url
validateUrlString(url);
url = getUrl(urlStr);
if (!url) {
logRecord.urlIsInvalid = true;
logRecord.error = 'Valid URL to parse not specified';
statusCode = 400;
return;
}
// pre handle url with custom handlers
try {
const browser = await getBrowserPromise;
const result = await preHandleContent(url, browser);
if (result && result.url) {
validateUrlString(url);
url = result.url;
}
if (result && result.title) { title = result.title }
if (result && result.content) { content = result.content }
if (result && result.contentType) { contentType = result.contentType }
} catch (e) {
console.info('error with handler: ', e);
}
if (result && result.title) { title = result.title }
if (result && result.content) { content = result.content }
if (result && result.contentType) { contentType = result.contentType }
} catch (e) {
console.info('error with handler: ', e);
}
let context, page, finalUrl, statusCode = 200;
try {
if ((!content || !title) && contentType !== 'application/pdf') {
const result = await retrievePage(url, logRecord, functionStartTime);
if (result && result.context) { context = result.context }
@ -412,7 +413,9 @@ async function fetchContent(req, res) {
console.error(`Error while retrieving page`, logRecord);
// fallback to scrapingbee for non pdf content
if (contentType !== 'application/pdf') {
if (url && contentType !== 'application/pdf') {
console.info('fallback to scrapingbee', url);
const fetchStartTime = Date.now();
const sbResult = await fetchContentWithScrapingBee(url);
content = sbResult.domContent;
@ -425,7 +428,7 @@ async function fetchContent(req, res) {
await context.close();
}
// save non pdf content
if (contentType !== 'application/pdf') {
if (url && contentType !== 'application/pdf') {
// parse content if it is not empty
let readabilityResult = null;
if (content) {
@ -507,8 +510,7 @@ function tryParseUrl(urlStr) {
}
}
function getUrl(req) {
const urlStr = (req.query ? req.query.url : undefined) || (req.body ? req.body.url : undefined);
function getUrl(urlStr) {
const url = tryParseUrl(urlStr)
if (!url) {
throw new Error('No URL specified');
@ -722,10 +724,10 @@ async function retrieveHtml(page, logRecord) {
// Replacing element only of there are no content inside, b/c might remove important div with content.
// Article example: http://www.josiahzayner.com/2017/01/genetic-designer-part-i.html
// DIV with class "content-inner" has `url("https://resources.blogblog.com/blogblog/data/1kt/travel/bg_container.png")` background image.
if (el.innerHTML.length < 25) {
if (!el.textContent) {
const img = document.createElement('img');
img.src = matchedSRC[1];
el && el.parentNode && el.parentNode.removeChild(el);
el && el.parentNode && el.parentNode.replaceChild(img, el);
}
}
}
@ -797,7 +799,8 @@ async function preview(req, res) {
return res.sendStatus(500);
}
const url = getUrl(req);
const urlStr = (req.query ? req.query.url : undefined) || (req.body ? req.body.url : undefined);
const url = getUrl(urlStr);
console.log('preview request url', url);
const logRecord = {

2
packages/readabilityjs/Readability.js
View File

@ -1059,6 +1059,8 @@ Readability.prototype = {
if (node.className === 'omnivore-published-date' && this._isValidPublishedDate(node.textContent)) {
return new Date(node.textContent);
}
// we don't want to check for dates in the URL's
if (node.tagName.toLowerCase() === 'a') return
// Searching for the real date in the text content
let dateRegExpFound = this.REGEXPS.DATES_REGEXPS.find(regexp => regexp.test(node.textContent.trim()))
dateRegExpFound && (dateRegExpFound = dateRegExpFound.exec(node.textContent.trim()))

4
packages/readabilityjs/test/generate-testcase.js
View File

@ -186,10 +186,10 @@ async function fetchSource(url, callbackFn) {
// Replacing element only of there are no content inside, b/c might remove important div with content.
// Article example: http://www.josiahzayner.com/2017/01/genetic-designer-part-i.html
// DIV with class "content-inner" has `url("https://resources.blogblog.com/blogblog/data/1kt/travel/bg_container.png")` background image.
if (el.innerHTML.length < 25) {
if (!el.textContent) {
const img = document.createElement('img');
img.src = matchedSRC[1];
el && el.parentNode && el.parentNode.removeChild(el);
el && el.parentNode && el.parentNode.replaceChild(img, el);
}
}
}

892
packages/readabilityjs/test/index.html
View File

@ -14,118 +14,40 @@
<td valign="top" style="width: 250px">
<ul>
<li>zhihu<br />
<a href="./test-pages/zhihu/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/zhihu/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/zhihu/distiller.html" target="iframe_b">[dom-distiller]</a>
<li>community.musictribe.com<br />
<a href="./test-pages/community.musictribe.com/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/community.musictribe.com/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/community.musictribe.com/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>medium<br />
<a href="./test-pages/medium/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/medium/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/medium/distiller.html" target="iframe_b">[dom-distiller]</a>
<li>moderndiplomacy<br />
<a href="./test-pages/moderndiplomacy/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/moderndiplomacy/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/moderndiplomacy/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>sydney.com<br />
<a href="./test-pages/sydney.com/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/sydney.com/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/sydney.com/distiller.html" target="iframe_b">[dom-distiller]</a>
<li>news.utexas<br />
<a href="./test-pages/news.utexas/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/news.utexas/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/news.utexas/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>sciencedirect<br />
<a href="./test-pages/sciencedirect/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/sciencedirect/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/sciencedirect/distiller.html" target="iframe_b">[dom-distiller]</a>
<li>nymag<br />
<a href="./test-pages/nymag/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/nymag/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/nymag/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>yuyue.com<br />
<a href="./test-pages/yuyue.com/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/yuyue.com/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/yuyue.com/distiller.html" target="iframe_b">[dom-distiller]</a>
<li>computerenhance.com<br />
<a href="./test-pages/computerenhance.com/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/computerenhance.com/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/computerenhance.com/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>vanityfair<br />
<a href="./test-pages/vanityfair/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/vanityfair/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/vanityfair/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>cnbc<br />
<a href="./test-pages/cnbc/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/cnbc/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/cnbc/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>channelnewsasia<br />
<a href="./test-pages/channelnewsasia/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/channelnewsasia/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/channelnewsasia/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>danwang<br />
<a href="./test-pages/danwang/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/danwang/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/danwang/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>github-blog<br />
<a href="./test-pages/github-blog/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/github-blog/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/github-blog/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>mathoverflow<br />
<a href="./test-pages/mathoverflow/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/mathoverflow/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/mathoverflow/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>www.musingmind.org<br />
<a href="./test-pages/www.musingmind.org/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/www.musingmind.org/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/www.musingmind.org/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>infoproc<br />
<a href="./test-pages/infoproc/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/infoproc/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/infoproc/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>gdcvault<br />
<a href="./test-pages/gdcvault/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/gdcvault/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/gdcvault/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>rootsofprogress<br />
<a href="./test-pages/rootsofprogress/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/rootsofprogress/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/rootsofprogress/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>guardian<br />
<a href="./test-pages/guardian/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/guardian/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/guardian/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>elidourado<br />
<a href="./test-pages/elidourado/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/elidourado/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/elidourado/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>variety<br />
<a href="./test-pages/variety/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/variety/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/variety/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>instyle<br />
<a href="./test-pages/instyle/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/instyle/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/instyle/distiller.html" target="iframe_b">[dom-distiller]</a>
<li>brookings.edu<br />
<a href="./test-pages/brookings.edu/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/brookings.edu/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/brookings.edu/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>ft.com<br />
@ -134,10 +56,382 @@
<a href="./test-pages/ft.com/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>gflownet<br />
<a href="./test-pages/gflownet/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/gflownet/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/gflownet/distiller.html" target="iframe_b">[dom-distiller]</a>
<li>www.musingmind.org<br />
<a href="./test-pages/www.musingmind.org/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/www.musingmind.org/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/www.musingmind.org/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>digital-garden-docs<br />
<a href="./test-pages/digital-garden-docs/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/digital-garden-docs/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/digital-garden-docs/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>thevaluable.dev<br />
<a href="./test-pages/thevaluable.dev/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/thevaluable.dev/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/thevaluable.dev/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>fiercepharma<br />
<a href="./test-pages/fiercepharma/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/fiercepharma/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/fiercepharma/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>aboveavalon<br />
<a href="./test-pages/aboveavalon/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/aboveavalon/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/aboveavalon/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>techcrunch<br />
<a href="./test-pages/techcrunch/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/techcrunch/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/techcrunch/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>kdnuggets<br />
<a href="./test-pages/kdnuggets/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/kdnuggets/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/kdnuggets/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>youtube-embed<br />
<a href="./test-pages/youtube-embed/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/youtube-embed/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/youtube-embed/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>people<br />
<a href="./test-pages/people/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/people/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/people/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>sciencedirect<br />
<a href="./test-pages/sciencedirect/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/sciencedirect/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/sciencedirect/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>city-journal<br />
<a href="./test-pages/city-journal/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/city-journal/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/city-journal/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>jacobbrazeal<br />
<a href="./test-pages/jacobbrazeal/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/jacobbrazeal/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/jacobbrazeal/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>slowboring<br />
<a href="./test-pages/slowboring/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/slowboring/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/slowboring/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>omnivore_getting_started<br />
<a href="./test-pages/omnivore_getting_started/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/omnivore_getting_started/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/omnivore_getting_started/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>berthub<br />
<a href="./test-pages/berthub/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/berthub/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/berthub/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>cavesocial<br />
<a href="./test-pages/cavesocial/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/cavesocial/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/cavesocial/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>telegr.ph<br />
<a href="./test-pages/telegr.ph/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/telegr.ph/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/telegr.ph/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>substack-michaelshellenberger<br />
<a href="./test-pages/substack-michaelshellenberger/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/substack-michaelshellenberger/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/substack-michaelshellenberger/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>biospace<br />
<a href="./test-pages/biospace/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/biospace/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/biospace/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>danwang<br />
<a href="./test-pages/danwang/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/danwang/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/danwang/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>financialpost-fishing-for-chips<br />
<a href="./test-pages/financialpost-fishing-for-chips/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/financialpost-fishing-for-chips/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/financialpost-fishing-for-chips/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>blog.jetbrains.com<br />
<a href="./test-pages/blog.jetbrains.com/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/blog.jetbrains.com/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/blog.jetbrains.com/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>channelnewsasia<br />
<a href="./test-pages/channelnewsasia/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/channelnewsasia/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/channelnewsasia/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>robinwieruch.de<br />
<a href="./test-pages/robinwieruch.de/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/robinwieruch.de/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/robinwieruch.de/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>variety<br />
<a href="./test-pages/variety/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/variety/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/variety/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>rootsofprogress<br />
<a href="./test-pages/rootsofprogress/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/rootsofprogress/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/rootsofprogress/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>habr.com<br />
<a href="./test-pages/habr.com/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/habr.com/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/habr.com/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>berthub-2<br />
<a href="./test-pages/berthub-2/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/berthub-2/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/berthub-2/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>moxie.org<br />
<a href="./test-pages/moxie.org/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/moxie.org/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/moxie.org/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>spakhm<br />
<a href="./test-pages/spakhm/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/spakhm/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/spakhm/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>sydney.com<br />
<a href="./test-pages/sydney.com/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/sydney.com/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/sydney.com/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>github-blog<br />
<a href="./test-pages/github-blog/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/github-blog/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/github-blog/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>fast-company<br />
<a href="./test-pages/fast-company/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/fast-company/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/fast-company/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>milkroad<br />
<a href="./test-pages/milkroad/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/milkroad/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/milkroad/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>stratechery<br />
<a href="./test-pages/stratechery/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/stratechery/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/stratechery/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>zhihu<br />
<a href="./test-pages/zhihu/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/zhihu/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/zhihu/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>channelnewsasia02<br />
<a href="./test-pages/channelnewsasia02/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/channelnewsasia02/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/channelnewsasia02/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>newsletters<br />
<a href="./test-pages/newsletters/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/newsletters/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/newsletters/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>jon.bo<br />
<a href="./test-pages/jon.bo/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/jon.bo/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/jon.bo/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>garymarcus<br />
<a href="./test-pages/garymarcus/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/garymarcus/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/garymarcus/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>danluu<br />
<a href="./test-pages/danluu/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/danluu/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/danluu/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>infoproc<br />
<a href="./test-pages/infoproc/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/infoproc/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/infoproc/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>vanityfair<br />
<a href="./test-pages/vanityfair/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/vanityfair/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/vanityfair/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>wechat<br />
<a href="./test-pages/wechat/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/wechat/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/wechat/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>stackoverflow<br />
<a href="./test-pages/stackoverflow/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/stackoverflow/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/stackoverflow/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>getting_started_with_omnivore<br />
<a href="./test-pages/getting_started_with_omnivore/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/getting_started_with_omnivore/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/getting_started_with_omnivore/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>jsomers<br />
<a href="./test-pages/jsomers/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/jsomers/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/jsomers/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>pontagedue<br />
<a href="./test-pages/pontagedue/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/pontagedue/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/pontagedue/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>bookofhook.blogspot.com<br />
<a href="./test-pages/bookofhook.blogspot.com/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/bookofhook.blogspot.com/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/bookofhook.blogspot.com/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>johnhcochrane.blogspot<br />
<a href="./test-pages/johnhcochrane.blogspot/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/johnhcochrane.blogspot/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/johnhcochrane.blogspot/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>china.substack<br />
<a href="./test-pages/china.substack/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/china.substack/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/china.substack/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>substack-email<br />
<a href="./test-pages/substack-email/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/substack-email/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/substack-email/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>elidourado<br />
<a href="./test-pages/elidourado/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/elidourado/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/elidourado/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>energias-renovables.com<br />
<a href="./test-pages/energias-renovables.com/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/energias-renovables.com/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/energias-renovables.com/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>mathoverflow<br />
<a href="./test-pages/mathoverflow/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/mathoverflow/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/mathoverflow/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>gdcvault<br />
<a href="./test-pages/gdcvault/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/gdcvault/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/gdcvault/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>debugger.medium<br />
<a href="./test-pages/debugger.medium/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/debugger.medium/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/debugger.medium/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>computer.rip<br />
<a href="./test-pages/computer.rip/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/computer.rip/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/computer.rip/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>erik-engheim<br />
<a href="./test-pages/erik-engheim/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/erik-engheim/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/erik-engheim/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>instyle<br />
<a href="./test-pages/instyle/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/instyle/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/instyle/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>electrek<br />
<a href="./test-pages/electrek/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/electrek/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/electrek/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>dailymail<br />
<a href="./test-pages/dailymail/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/dailymail/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/dailymail/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>lesswrong<br />
<a href="./test-pages/lesswrong/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/lesswrong/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/lesswrong/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>ottawacitizen.com<br />
@ -152,334 +446,16 @@
<a href="./test-pages/nytimes/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>stratechery<br />
<a href="./test-pages/stratechery/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/stratechery/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/stratechery/distiller.html" target="iframe_b">[dom-distiller]</a>
<li>yuyue.com<br />
<a href="./test-pages/yuyue.com/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/yuyue.com/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/yuyue.com/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>danluu<br />
<a href="./test-pages/danluu/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/danluu/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/danluu/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>financialpost-fishing-for-chips<br />
<a href="./test-pages/financialpost-fishing-for-chips/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/financialpost-fishing-for-chips/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/financialpost-fishing-for-chips/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>wechat<br />
<a href="./test-pages/wechat/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/wechat/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/wechat/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>samcurry<br />
<a href="./test-pages/samcurry/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/samcurry/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/samcurry/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>thevaluable.dev<br />
<a href="./test-pages/thevaluable.dev/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/thevaluable.dev/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/thevaluable.dev/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>jacobbrazeal<br />
<a href="./test-pages/jacobbrazeal/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/jacobbrazeal/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/jacobbrazeal/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>fiercepharma<br />
<a href="./test-pages/fiercepharma/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/fiercepharma/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/fiercepharma/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>brookings.edu<br />
<a href="./test-pages/brookings.edu/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/brookings.edu/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/brookings.edu/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>nytimes.com<br />
<a href="./test-pages/nytimes.com/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/nytimes.com/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/nytimes.com/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>stackoverflow<br />
<a href="./test-pages/stackoverflow/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/stackoverflow/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/stackoverflow/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>blog.jetbrains.com<br />
<a href="./test-pages/blog.jetbrains.com/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/blog.jetbrains.com/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/blog.jetbrains.com/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>bookofhook.blogspot.com<br />
<a href="./test-pages/bookofhook.blogspot.com/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/bookofhook.blogspot.com/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/bookofhook.blogspot.com/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>channelnewsasia02<br />
<a href="./test-pages/channelnewsasia02/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/channelnewsasia02/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/channelnewsasia02/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>aboveavalon<br />
<a href="./test-pages/aboveavalon/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/aboveavalon/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/aboveavalon/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>josephg<br />
<a href="./test-pages/josephg/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/josephg/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/josephg/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>city-journal<br />
<a href="./test-pages/city-journal/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/city-journal/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/city-journal/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>slowboring<br />
<a href="./test-pages/slowboring/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/slowboring/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/slowboring/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>ahhhhfs.com<br />
<a href="./test-pages/ahhhhfs.com/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/ahhhhfs.com/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/ahhhhfs.com/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>techcrunch<br />
<a href="./test-pages/techcrunch/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/techcrunch/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/techcrunch/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>habr.com<br />
<a href="./test-pages/habr.com/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/habr.com/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/habr.com/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>telegr.ph<br />
<a href="./test-pages/telegr.ph/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/telegr.ph/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/telegr.ph/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>bitfieldconsulting<br />
<a href="./test-pages/bitfieldconsulting/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/bitfieldconsulting/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/bitfieldconsulting/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>garymarcus<br />
<a href="./test-pages/garymarcus/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/garymarcus/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/garymarcus/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>substack-email<br />
<a href="./test-pages/substack-email/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/substack-email/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/substack-email/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>newsletters<br />
<a href="./test-pages/newsletters/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/newsletters/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/newsletters/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>computerenhance.com<br />
<a href="./test-pages/computerenhance.com/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/computerenhance.com/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/computerenhance.com/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>nymag<br />
<a href="./test-pages/nymag/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/nymag/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/nymag/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>milkroad<br />
<a href="./test-pages/milkroad/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/milkroad/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/milkroad/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>getting_started_with_omnivore<br />
<a href="./test-pages/getting_started_with_omnivore/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/getting_started_with_omnivore/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/getting_started_with_omnivore/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>news.utexas<br />
<a href="./test-pages/news.utexas/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/news.utexas/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/news.utexas/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>johnhcochrane.blogspot<br />
<a href="./test-pages/johnhcochrane.blogspot/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/johnhcochrane.blogspot/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/johnhcochrane.blogspot/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>fast-company<br />
<a href="./test-pages/fast-company/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/fast-company/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/fast-company/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>community.musictribe.com<br />
<a href="./test-pages/community.musictribe.com/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/community.musictribe.com/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/community.musictribe.com/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>moderndiplomacy<br />
<a href="./test-pages/moderndiplomacy/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/moderndiplomacy/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/moderndiplomacy/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>energias-renovables.com<br />
<a href="./test-pages/energias-renovables.com/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/energias-renovables.com/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/energias-renovables.com/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>computer.rip<br />
<a href="./test-pages/computer.rip/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/computer.rip/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/computer.rip/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>berthub-2<br />
<a href="./test-pages/berthub-2/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/berthub-2/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/berthub-2/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>lesswrong<br />
<a href="./test-pages/lesswrong/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/lesswrong/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/lesswrong/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>youtube-embed<br />
<a href="./test-pages/youtube-embed/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/youtube-embed/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/youtube-embed/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>biospace<br />
<a href="./test-pages/biospace/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/biospace/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/biospace/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>substack-michaelshellenberger<br />
<a href="./test-pages/substack-michaelshellenberger/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/substack-michaelshellenberger/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/substack-michaelshellenberger/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>china.substack<br />
<a href="./test-pages/china.substack/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/china.substack/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/china.substack/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>dailymail<br />
<a href="./test-pages/dailymail/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/dailymail/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/dailymail/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>people<br />
<a href="./test-pages/people/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/people/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/people/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>robinwieruch.de<br />
<a href="./test-pages/robinwieruch.de/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/robinwieruch.de/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/robinwieruch.de/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>spakhm<br />
<a href="./test-pages/spakhm/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/spakhm/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/spakhm/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>cavesocial<br />
<a href="./test-pages/cavesocial/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/cavesocial/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/cavesocial/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>omnivore_getting_started<br />
<a href="./test-pages/omnivore_getting_started/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/omnivore_getting_started/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/omnivore_getting_started/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>electrek<br />
<a href="./test-pages/electrek/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/electrek/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/electrek/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>berthub<br />
<a href="./test-pages/berthub/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/berthub/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/berthub/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>jsomers<br />
<a href="./test-pages/jsomers/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/jsomers/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/jsomers/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>debugger.medium<br />
<a href="./test-pages/debugger.medium/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/debugger.medium/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/debugger.medium/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>jon.bo<br />
<a href="./test-pages/jon.bo/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/jon.bo/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/jon.bo/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>kdnuggets<br />
<a href="./test-pages/kdnuggets/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/kdnuggets/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/kdnuggets/distiller.html" target="iframe_b">[dom-distiller]</a>
<li>cnbc<br />
<a href="./test-pages/cnbc/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/cnbc/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/cnbc/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>nytimes-podcasts<br />
@ -488,16 +464,52 @@
<a href="./test-pages/nytimes-podcasts/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>erik-engheim<br />
<a href="./test-pages/erik-engheim/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/erik-engheim/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/erik-engheim/distiller.html" target="iframe_b">[dom-distiller]</a>
<li>gflownet<br />
<a href="./test-pages/gflownet/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/gflownet/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/gflownet/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>moxie.org<br />
<a href="./test-pages/moxie.org/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/moxie.org/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/moxie.org/distiller.html" target="iframe_b">[dom-distiller]</a>
<li>medium<br />
<a href="./test-pages/medium/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/medium/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/medium/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>guardian<br />
<a href="./test-pages/guardian/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/guardian/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/guardian/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>ahhhhfs.com<br />
<a href="./test-pages/ahhhhfs.com/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/ahhhhfs.com/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/ahhhhfs.com/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>bitfieldconsulting<br />
<a href="./test-pages/bitfieldconsulting/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/bitfieldconsulting/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/bitfieldconsulting/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>samcurry<br />
<a href="./test-pages/samcurry/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/samcurry/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/samcurry/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>nytimes.com<br />
<a href="./test-pages/nytimes.com/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/nytimes.com/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/nytimes.com/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
<li>josephg<br />
<a href="./test-pages/josephg/source.html" target="iframe_b">[source]</a>
<a href="./test-pages/josephg/expected.html" target="iframe_b">[readability]</a>
<a href="./test-pages/josephg/distiller.html" target="iframe_b">[dom-distiller]</a>
</li>
</ul>

13
packages/readabilityjs/test/test-pages/digital-garden-docs/distiller.html Normal file
View File

@ -0,0 +1,13 @@
<div><h1>
🏡
</h1><h1 tabindex="-1">
Obsidian Digital Garden
</h1><p>
The <a href="https://github.com/oleeskild/obsidian-digital-garden" target="_blank">Obsidian Digital Garden Plugin</a> is a free and open source publishing tool for <a href="https://obsidian.md" target="_blank">Obsidian</a>.
</p><p>
Publish your notes directly from <a href="https://obsidian.md/" target="_blank">Obsidian</a> to the internet. While <a href="/features/">feature packed</a>, it is <a href="/getting-started/03-note-settings/">highly configurable</a> and <a href="/advanced/adding-custom-components/">hackable</a>. Enable and disable features on a per-note basis. Use it as a full fledged digital garden or as a <a href="/example-pages/simple-page/">simple note sharing solution</a>.
</p><h2 tabindex="-1">
Examples
</h2><p>
This site is itself powered by the Digital Garden plugin.
</p></div>

11
packages/readabilityjs/test/test-pages/digital-garden-docs/expected-metadata.json Normal file
View File

@ -0,0 +1,11 @@
{
"title": "Digital Garden Overview",
"byline": null,
"dir": null,
"excerpt": "The Obsidian Digital Garden Plugin is a free and open source publishing tool for Obsidian.",
"siteName": "fakehost",
"siteIcon": "http://fakehost/favicon.ico",
"publishedDate": null,
"language": "English",
"readerable": false
}

52
packages/readabilityjs/test/test-pages/digital-garden-docs/expected.html Normal file
View File

@ -0,0 +1,52 @@
<DIV class="page" id="readability-page-1">
<DIV>
<header>
</header>
<h2> 🏡 </h2>
<h2 tabindex="-1" id="obsidian-digital-garden"> Obsidian Digital Garden </h2>
<p> The <a href="https://github.com/oleeskild/obsidian-digital-garden" target="_blank">Obsidian Digital Garden Plugin</a> is a free and open source publishing tool for <a href="https://obsidian.md/" target="_blank">Obsidian</a>. </p>
<p> Publish your notes directly from <a href="https://obsidian.md/" target="_blank">Obsidian</a> to the internet. While <a href="http://fakehost/features/">feature packed</a>, it is <a href="http://fakehost/getting-started/03-note-settings/">highly configurable</a> and <a href="http://fakehost/advanced/adding-custom-components/">hackable</a>. Enable and disable features on a per-note basis. Use it as a full fledged digital garden or as a <a href="http://fakehost/example-pages/simple-page/">simple note sharing solution</a>. </p>
<p> 👉 <a href="http://fakehost/getting-started/01-getting-started/">Getting Started</a><br> 👉 <a href="http://fakehost/features/">Features</a>
</p>
<h2 id="examples" tabindex="-1"> Examples </h2>
<p> This site is itself powered by the Digital Garden plugin. </p>
<div>
<div>
<p><img src="https://res.cloudinary.com/dix4ngy25/image/upload/c_scale,r_8,w_300/v1668690350/dgdocs/CleanShot_2022-11-17_at_14.05.20_2x.png"> <a href="https://edav-garden.netlify.app/" target="_blank">Edav Garden</a>
</p>
</div>
<div>
<p><img src="https://res.cloudinary.com/dix4ngy25/image/upload/c_scale,r_8,w_300/v1668500110/dgdocs/CleanShot_2022-11-15_at_09.14.26_2x.png"> <a href="https://ajy.co/" target="_blank">ajy.co</a>
</p>
</div>
<div>
<p><img src="https://res.cloudinary.com/dix4ngy25/image/upload/c_scale,r_8,w_300/v1672992556/dgdocs/CleanShot_2023-02-05_at_20.18.45_2x"> <a href="https://hermitage.utsob.me/" target="_blank">Hermitage</a>
</p>
</div>
<div>
<p><img src="https://res.cloudinary.com/dix4ngy25/image/upload/c_scale,r_8,w_300/v1668068263/dgdocs/CleanShot_2022-11-10_at_09.17.28_2x.png"> <a href="https://notes.thatother.dev/" target="_blank">That Other Dev</a>
</p>
</div>
<div>
<p><img src="https://res.cloudinary.com/dix4ngy25/image/upload/c_scale,r_8,w_300/v1668500118/dgdocs/CleanShot_2022-11-15_at_09.14.17_2x.png"> <a href="https://razvan-andrei-surdu.eu/" target="_blank">Razvan Andrei Surdu</a>
</p>
</div>
<div>
<p><img src="https://res.cloudinary.com/dix4ngy25/image/upload/c_scale,r_8,w_300/v1668068103/dgdocs/CleanShot_2023-02-05_at_20.17.02_2x"> <a href="https://icewind.quest/" target="_blank">IceWind.Quest</a>
</p>
</div>
<div>
<p><img src="https://res.cloudinary.com/dix4ngy25/image/upload/c_scale,r_8,w_300/v1668068358/dgdocs/CleanShot_2022-11-10_at_09.19.06_2x.png"> <a href="https://notes.hxhc.xyz/" target="_blank">hxhc</a>
</p>
</div>
<div>
<p><img src="https://res.cloudinary.com/dix4ngy25/image/upload/c_scale,r_8,w_300/v1671387169/dgdocs/CleanShot_2022-12-18_at_19.12.28_2x.png"> <a href="https://notes.ole.dev/" target="_blank">notes.ole.dev</a>
</p>
</div>
</div>
<div>
<p><a href="https://github.com/oleeskild/obsidian-digital-garden/issues/55" target="_blank"><button>Submit your site</button></a>
</p>
</div>
</DIV>
</DIV>

1259
packages/readabilityjs/test/test-pages/digital-garden-docs/source.html Normal file
View File

File diff suppressed because it is too large Load Diff

1
packages/readabilityjs/test/test-pages/digital-garden-docs/url.txt Normal file
View File

@ -0,0 +1 @@
https://dg-docs.ole.dev/

40
packages/readabilityjs/test/test-pages/pontagedue/distiller.html Normal file
View File

@ -0,0 +1,40 @@
<div><p>
I’m minding my own business, wandering around the Internet when I am smacked in the eyes by an interesting blog title – “Dwarf begone! Five early medieval ways to rid yourself of dwarfs” (<a href="https://thijsporck.com/2020/05/03/dwarf-begone/">https://thijsporck.com/2020/05/03/dwarf-begone/</a>)<br/>
<br/>
I believe it is the worst kept secret that I tend to be easily earwormed, and an even worse kept one that a “song” called Diggy, Diggy hole is particular effective as a weaponised version. (I recommend the Wind Rose version if you need to check it out) I was amused, then, to read:
</p><p>
<br/>
“The charm [found among the <em>Lacnunga</em>, instructs one to take seven little wafers like the ones people use to worship; i.e. the Host] and write down the names of seven saints (Maximianus, Malcus, Johannes, Martinianus, Dionysius, Constantinus and Serafion – the names of the Christian saints collectively known as the Seven Sleepers)] further instructs that a virgin must hang these wafers around the neck of the patient and that you are to sing a particular song, “ærest on þæt wynstre eare, þænne on þæt swiðre eare, þænne bufan þæs mannes moldan” [first into the left ear, then into the right ear, then on top of the patient’s head]. This ritual is to be repeated for three days in a row”<br/>
<br/>
So earworm a man to rid him of a dwarf – Interesting! Why would a medieval person have wanted to do such a thing?
</p><p>
“The Old English word for dwarf, <em>dweorg</em>, could also denote “fever, perhaps high fever with delirium and convulsions” [<em><a rel="noreferrer noopener" href="https://www.doe.utoronto.ca/pages/index.html" target="_blank">Dictionary of Old English</a></em>, s.v. <em>dweorg</em>]”
</p><p>
The blogpost offers the following as the generally accepted translation of Harley MS 585, fol. 167v
</p><p>
Here came a spider-creature crawling in;<br/>
His web was a harness held in his hand.<br/>
Stalking, he said that you were his steed.<br/>
Then he threw his net around your neck,<br/>
Reining you in. Then they both began<br/>
To rise from the land, spring from the earth.<br/>
As they leapt up, their limbs grew cool.<br/>
Then the spider-dwarf’s sister jumped in,<br/>
Ending it all by swearing these oaths:<br/>
No hurt should come to harm the sick,<br/>
No pain to the patient who receives the cure,<br/>
No harm to the one who sings this charm.
</p><p>
Amen. Let it be done. ] (Trans. Williamson 2017, p. 1075)
</p><p>
I LOVE the image of a shady “spiderwiht” (awesome word) attempting to ride a man and making him writhe and convulse with fever as a result.
</p><p>
I was also amused at the idea of using a skull fragment to inscribe the runes “DEAD IS DWERG” on as a talisman against dwarves, but, you know, I love my household, I’m sure I would never resort to such things..<br/>
</p><figure><img src="https://pontagedue.files.wordpress.com/2023/06/60948_63179c_ms_inscribedobject_detail.jpg?w=500" alt="" srcset="https://pontagedue.files.wordpress.com/2023/06/60948_63179c_ms_inscribedobject_detail.jpg 500w, https://pontagedue.files.wordpress.com/2023/06/60948_63179c_ms_inscribedobject_detail.jpg?w=150 150w, https://pontagedue.files.wordpress.com/2023/06/60948_63179c_ms_inscribedobject_detail.jpg?w=300 300w" sizes="(max-width: 500px) 100vw, 500px"/></figure><p>
Rights Holder: Norfolk County Council<br/>
CC License: By-SA – <a href="https://finds.org.uk/database/artefacts/record/id/751600" rel="nofollow">https://finds.org.uk/database/artefacts/record/id/751600</a>
</p><p>
It’s an interesting article. I’ll shut up now. No singing here, no, uh uh…. <em>brothers of the mine..</em> damnnnnnnnn<br/>
</p><div>
Advertisement
</div></div>

12
packages/readabilityjs/test/test-pages/pontagedue/expected-metadata.json Normal file
View File

@ -0,0 +1,12 @@
{
"title": "DEAD IS DWERG",
"byline": null,
"dir": null,
"excerpt": "I'm minding my own business, wandering around the Internet when I am smacked in the eyes by an interesting blog title - \"Dwarf begone! Five early medieval ways to rid yourself of dwarfs\" (https://thijsporck.com/2020/05/03/dwarf-begone/) I believe it is the worst kept secret that I tend to be easily earwormed, and an even worse kept one…",
"siteName": "Time traveling Órlaith",
"siteIcon": "https://s0.wp.com/i/favicon.ico",
"previewImage": "https://pontagedue.files.wordpress.com/2023/06/60948_63179c_ms_inscribedobject_detail.jpg?w=640",
"publishedDate": "2023-06-20T22:24:10.000Z",
"language": "English",
"readerable": true
}

29
packages/readabilityjs/test/test-pages/pontagedue/expected.html Normal file
View File

@ -0,0 +1,29 @@
<DIV class="page" id="readability-page-1">
<article id="post-3917">
<!-- .entry-media -->
<div>
<DIV data-adtags-visited="true">
<p> I’m minding my own business, wandering around the Internet when I am smacked in the eyes by an interesting blog title – “Dwarf begone! Five early medieval ways to rid yourself of dwarfs” (<a href="https://thijsporck.com/2020/05/03/dwarf-begone/">https://thijsporck.com/2020/05/03/dwarf-begone/</a>)</p>
<p> I believe it is the worst kept secret that I tend to be easily earwormed, and an even worse kept one that a “song” called Diggy, Diggy hole is particular effective as a weaponised version. (I recommend the Wind Rose version if you need to check it out) I was amused, then, to read: </p>
</DIV>
<DIV data-adtags-visited="true">
<p> “The charm [found among the&nbsp;<em>Lacnunga</em>, instructs one to take seven little wafers like the ones people use to worship; i.e. the Host] and write down the names of seven saints (Maximianus, Malcus, Johannes, Martinianus, Dionysius, Constantinus and Serafion – the names of the Christian saints collectively known as the Seven Sleepers)] further instructs that a virgin must hang these wafers around the neck of the patient and that you are to sing a particular song, “ærest on þæt wynstre eare, þænne on þæt swiðre eare, þænne bufan þæs mannes moldan” [first into the left ear, then into the right ear, then on top of the patient’s head]. This ritual is to be repeated for three days in a row”</p>
<p> So earworm a man to rid him of a dwarf – Interesting! Why would a medieval person have wanted to do such a thing? </p>
</DIV>
<p data-adtags-visited="true"> “The Old English word for dwarf,&nbsp;<em>dweorg</em>, could also denote “fever, perhaps high fever with delirium and convulsions” [<em><a rel="noreferrer noopener" href="https://www.doe.utoronto.ca/pages/index.html" target="_blank">Dictionary of Old English</a></em>, s.v.&nbsp;<em>dweorg</em>]” </p>
<p data-adtags-visited="true"> The blogpost offers the following as the generally accepted translation of Harley MS 585, fol. 167v </p>
<p data-adtags-visited="true"> Here came a spider-creature crawling in;<br> His web was a harness held in his hand.<br> Stalking, he said that you were his steed.<br> Then he threw his net around your neck,<br> Reining you in. Then they both began<br> To rise from the land, spring from the earth.<br> As they leapt up, their limbs grew cool.<br> Then the spider-dwarf’s sister jumped in,<br> Ending it all by swearing these oaths:<br> No hurt should come to harm the sick,<br> No pain to the patient who receives the cure,<br> No harm to the one who sings this charm. </p>
<p data-adtags-visited="true"> Amen. Let it be done. ] (Trans. Williamson 2017, p. 1075) </p>
<p data-adtags-visited="true"> I LOVE the image of a shady “spiderwiht” (awesome word) attempting to ride a man and making him writhe and convulse with fever as a result. </p>
<p data-adtags-visited="true"> I was also amused at the idea of using a skull fragment to inscribe the runes “DEAD IS DWERG” on as a talisman against dwarves, but, you know, I love my household, I’m sure I would never resort to such things..<br>
</p>
<figure>
<a href="https://pontagedue.files.wordpress.com/2023/06/60948_63179c_ms_inscribedobject_detail.jpg"><img data-attachment-id="3926" data-permalink="https://pontagedue.wordpress.com/2023/06/20/dead-is-dwerg/60948_63179c_ms_inscribedobject_detail/" data-orig-file="https://pontagedue.files.wordpress.com/2023/06/60948_63179c_ms_inscribedobject_detail.jpg" data-orig-size="500,266" data-comments-opened="1" data-image-meta="{&quot;aperture&quot;:&quot;0&quot;,&quot;credit&quot;:&quot;&quot;,&quot;camera&quot;:&quot;&quot;,&quot;caption&quot;:&quot;&quot;,&quot;created_timestamp&quot;:&quot;0&quot;,&quot;copyright&quot;:&quot;&quot;,&quot;focal_length&quot;:&quot;0&quot;,&quot;iso&quot;:&quot;0&quot;,&quot;shutter_speed&quot;:&quot;0&quot;,&quot;title&quot;:&quot;&quot;,&quot;orientation&quot;:&quot;0&quot;}" data-image-title="60948_63179c_ms_inscribedobject_detail" data-image-description="" data-image-caption="" data-medium-file="https://pontagedue.files.wordpress.com/2023/06/60948_63179c_ms_inscribedobject_detail.jpg?w=300" data-large-file="https://pontagedue.files.wordpress.com/2023/06/60948_63179c_ms_inscribedobject_detail.jpg?w=500" src="https://pontagedue.files.wordpress.com/2023/06/60948_63179c_ms_inscribedobject_detail.jpg?w=500" alt="" srcset="https://pontagedue.files.wordpress.com/2023/06/60948_63179c_ms_inscribedobject_detail.jpg 500w, https://pontagedue.files.wordpress.com/2023/06/60948_63179c_ms_inscribedobject_detail.jpg?w=150 150w, https://pontagedue.files.wordpress.com/2023/06/60948_63179c_ms_inscribedobject_detail.jpg?w=300 300w" sizes="(max-width: 500px) 100vw, 500px"></a>
</figure>
<p data-adtags-visited="true"> Rights Holder: Norfolk County Council<br> CC License:&nbsp;By-SA – <a href="https://finds.org.uk/database/artefacts/record/id/751600" rel="nofollow">https://finds.org.uk/database/artefacts/record/id/751600</a>
</p>
<p data-adtags-visited="true"> It’s an interesting article. I’ll shut up now. No singing here, no, uh uh…. <em>brothers of the mine..</em> damnnnnnnnn<br>
</p>
</div><!-- .entry-inner -->
</article>
</DIV>

1680
packages/readabilityjs/test/test-pages/pontagedue/source.html Normal file
View File

File diff suppressed because one or more lines are too long

1
packages/readabilityjs/test/test-pages/pontagedue/url.txt Normal file
View File

@ -0,0 +1 @@
https://pontagedue.wordpress.com/2023/06/20/dead-is-dwerg/