diff --git a/src/parser.js b/src/parser.js
index 683344c..99ca1ba 100644
--- a/src/parser.js
+++ b/src/parser.js
@@ -113,7 +113,7 @@ function getPostCoverImageId(postData) {
function collectAttachedImages(channelData) {
const images = getItemsOfType(channelData, 'attachment')
// filter to certain image file types
- .filter(attachment => attachment.attachment_url && (/\.(gif|jpe?g|png)$/i).test(attachment.attachment_url[0]))
+ .filter(attachment => attachment.attachment_url && (/\.(gif|jpe?g|png|webp)$/i).test(attachment.attachment_url[0]))
.map(attachment => ({
id: attachment.post_id[0],
postId: attachment.post_parent[0],
@@ -132,7 +132,7 @@ function collectScrapedImages(channelData, postTypes) {
const postContent = postData.encoded[0];
const postLink = postData.link[0];
- const matches = [...postContent.matchAll(/
]*src="(.+?\.(?:gif|jpe?g|png))"[^>]*>/gi)];
+ const matches = [...postContent.matchAll(/
]*src="(.+?\.(?:gif|jpe?g|png|webp))"[^>]*>/gi)];
matches.forEach(match => {
// base the matched image URL relative to the post URL
const url = new URL(match[1], postLink).href;
diff --git a/src/translator.js b/src/translator.js
index 2a24452..c974599 100644
--- a/src/translator.js
+++ b/src/translator.js
@@ -105,7 +105,7 @@ function getPostContent(postData, turndownService, config) {
if (config.saveScrapedImages) {
// writeImageFile() will save all content images to a relative /images
// folder so update references in post content to match
- content = content.replace(/(
]*src=").*?([^/"]+\.(?:gif|jpe?g|png))("[^>]*>)/gi, '$1images/$2$3');
+ content = content.replace(/(
]*src=").*?([^/"]+\.(?:gif|jpe?g|png|webp))("[^>]*>)/gi, '$1images/$2$3');
}
// preserve "more" separator, max one per post, optionally with custom label
diff --git a/src/wizard.js b/src/wizard.js
index 5285b8d..88a722d 100644
--- a/src/wizard.js
+++ b/src/wizard.js
@@ -74,6 +74,12 @@ const options = [
type: 'boolean',
description: 'Include custom post types and pages',
default: false
+ },
+ {
+ name: 'disable-strict-ssl',
+ type: 'boolean',
+ description: 'Strict SSL prevents image retrieval from self-signed servers',
+ default: false
}
];
diff --git a/src/writer.js b/src/writer.js
index b782756..fa02ce1 100644
--- a/src/writer.js
+++ b/src/writer.js
@@ -16,7 +16,7 @@ async function processPayloadsPromise(payloads, loadFunc) {
const promises = payloads.map(payload => new Promise((resolve, reject) => {
setTimeout(async () => {
try {
- const data = await loadFunc(payload.item);
+ const data = await loadFunc(payload.item, payload.strictSSL);
await writeFile(payload.destinationPath, data);
console.log(chalk.green('[OK]') + ' ' + payload.name);
resolve();
@@ -55,6 +55,7 @@ async function writeMarkdownFilesPromise(posts, config ) {
const payload = {
item: post,
name: (config.includeOtherTypes ? post.meta.type + ' - ' : '') + post.meta.slug,
+ strictSSL: !config.disableStrictSsl,
destinationPath,
delay
};
@@ -72,7 +73,7 @@ async function writeMarkdownFilesPromise(posts, config ) {
}
}
-async function loadMarkdownFilePromise(post) {
+async function loadMarkdownFilePromise(post, strictSSL) {
let output = '---\n';
Object.entries(post.frontmatter).forEach(([key, value]) => {
@@ -117,6 +118,7 @@ async function writeImageFilesPromise(posts, config) {
const payload = {
item: imageUrl,
name: filename,
+ strictSSL: !config.disableStrictSsl,
destinationPath,
delay
};
@@ -135,7 +137,7 @@ async function writeImageFilesPromise(posts, config) {
}
}
-async function loadImageFilePromise(imageUrl) {
+async function loadImageFilePromise(imageUrl, strictSSL) {
// only encode the URL if it doesn't already have encoded characters
const url = (/%[\da-f]{2}/i).test(imageUrl) ? imageUrl : encodeURI(imageUrl);
@@ -146,7 +148,8 @@ async function loadImageFilePromise(imageUrl) {
encoding: null, // preserves binary encoding
headers: {
'User-Agent': 'wordpress-export-to-markdown'
- }
+ },
+ strictSSL: strictSSL
});
} catch (ex) {
if (ex.name === 'StatusCodeError') {