Il Post #3240
Open
Il Post #3240
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
AbeJellinek
requested changes
Feb 8, 2024
| return 'multiple'; | ||
| } | ||
| else { | ||
| return 'newspaperArticle'; |
There was a problem hiding this comment.
Check that it's actually an article - we don't want to capture the home page as a newspaperArticle, for instance.
| // TODO | ||
| // return 'blogPost'; | ||
| } | ||
| else if (url.includes('/cerca/')) { |
There was a problem hiding this comment.
Suggested change
| else if (url.includes('/cerca/')) { | |
| else if (url.includes('/cerca/') && getSearchResults(doc, true)) { |
Comment on lines
+72
to
+92
| async function doWeb(doc, url) { | ||
| await doWebInternal(doc, url, true); | ||
| } | ||
|
|
||
| async function doWebInternal(doc, url, includeSearch) { | ||
| switch (detectWeb(doc, url)) { | ||
| case 'newspaperArticle': | ||
| await scrapeArticle(doc, url); | ||
| break; | ||
| case 'multiple': | ||
| if (!includeSearch) return; | ||
| let searchResults = getSearchResults(doc, false); | ||
| if (!searchResults) return; | ||
| let items = await Zotero.selectItems(getSearchResults(doc, false)); | ||
| if (!items) return; | ||
| for (let url of Object.keys(items)) { | ||
| await doWebInternal(await requestDocument(url), url, false); | ||
| } | ||
| break; | ||
| } | ||
| } |
There was a problem hiding this comment.
Can just move the contents of doWebInternal() to doWeb() and call scrapeArticle() directly in the multiple handler.
| } | ||
| } | ||
|
|
||
| const ISSN = '2610-9980'; |
| let sections = []; | ||
| for (let taxonomy of taxonomyData) { | ||
| if (!taxonomy.name) continue; | ||
| switch (taxonomy?.taxonomy) { |
There was a problem hiding this comment.
Suggested change
| switch (taxonomy?.taxonomy) { | |
| switch (taxonomy.taxonomy) { |
Not much good in using a short-circuiting operator when we've already accessed taxonomy.name above.
| break; | ||
| } | ||
| } | ||
| if (sections.length > 0) item.section = sections.sort().join(', '); |
There was a problem hiding this comment.
If they're tags, we should be putting them in item.tags. I don't think there's often a good reason to put multiple things into item.section.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Translator for Italian newspaper Il Post. Supports articles and search pages. Recognizes but does not support podcasts and newsletters yet