fix(meta-tags): add workaround for Preflight-Audit #1216
There are no files selected for viewing
This file contains hidden or 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
| Original file line number | Diff line number | Diff line change |
|---|---|---|
|
|
@@ -13,13 +13,12 @@ | |
| import RUMAPIClient from '@adobe/spacecat-shared-rum-api-client'; | ||
| import { Audit } from '@adobe/spacecat-shared-data-access'; | ||
| import { calculateCPCValue } from '../support/utils.js'; | ||
| import { getObjectFromKey } from '../utils/s3-utils.js'; | ||
| import SeoChecks from './seo-checks.js'; | ||
| import { AuditBuilder } from '../common/audit-builder.js'; | ||
| import { wwwUrlResolver } from '../common/index.js'; | ||
| import metatagsAutoSuggest from './metatags-auto-suggest.js'; | ||
| import { convertToOpportunity } from '../common/opportunity.js'; | ||
| import { getIssueRanking, getBaseUrl } from './opportunity-utils.js'; | ||
| import { | ||
| DESCRIPTION, | ||
|
|
@@ -90,7 +89,7 @@ export async function opportunityAndSuggestions(finalUrl, auditData, context) { | |
| log.info(`Successfully synced Opportunity And Suggestions for site: ${auditData.siteId} and ${auditType} audit type.`); | ||
| } | ||
|
|
||
| export async function fetchAndProcessPageObject(s3Client, bucketName, url, key, log) { | ||
| const object = await getObjectFromKey(s3Client, bucketName, key, log); | ||
| if (!object?.scrapeResult?.tags || typeof object.scrapeResult.tags !== 'object') { | ||
| log.error(`No Scraped tags found in S3 ${key} object`); | ||
|
|
@@ -102,12 +101,9 @@ export async function fetchAndProcessPageObject(s3Client, bucketName, key, prefi | |
| return null; | ||
| } | ||
|
|
||
| const pageUrl = object.finalUrl ? new URL(object.finalUrl).pathname | ||
| : new URL(url).pathname; | ||
| // handling for homepage | ||
| return { | ||
| [pageUrl]: { | ||
| title: object.scrapeResult.tags.title, | ||
|
|
@@ -206,24 +202,21 @@ async function calculateProjectedTraffic(context, site, detectedTags, log) { | |
| } | ||
| } | ||
|
|
||
| export async function metatagsAutoDetect(site, pagesMap, context) { | ||
| const { log, s3Client } = context; | ||
| // Fetch site's scraped content from S3 | ||
| const bucketName = context.env.S3_SCRAPER_BUCKET_NAME; | ||
| const extractedTags = {}; | ||
| const pageMetadataResults = await Promise.all([...pagesMap] | ||
| .map(([url, path]) => fetchAndProcessPageObject(s3Client, bucketName, url, path, log))); | ||
| pageMetadataResults.forEach((pageMetadata) => { | ||
| if (pageMetadata) { | ||
| Object.assign(extractedTags, pageMetadata); | ||
| } | ||
| }); | ||
| const extractedTagsCount = Object.entries(extractedTags).length; | ||
| if (extractedTagsCount === 0) { | ||
| log.error(`Failed to extract tags from scraped content for bucket ${bucketName}`); | ||
| } | ||
|
|
||
| // Perform SEO checks | ||
|
|
@@ -242,38 +235,16 @@ export async function metatagsAutoDetect(site, pagesSet, context) { | |
| }; | ||
| } | ||
|
|
||
| export async function runAuditAndGenerateSuggestions(context) { | ||
| const { | ||
| site, audit, finalUrl, log, scrapeResultPaths, | ||
| } = context; | ||
|
There was a problem hiding this comment. Since this code is now removed, will the scrapeResultPaths coming from context ensure it only contain the latest top-pages scrapes, and no older scrapes (from previous top-pages imports)? There was a problem hiding this comment. scrapeResultPaths will only contain URLs that were originally submitted for scraping by this audit. the new scrapeClient workflow will ensure that. |
||
|
There was a problem hiding this comment. Since this code is now removed, how are we incorporating the includedUrls in the meta-tags audit? There was a problem hiding this comment. we use all URLs that were successfully scraped. in the |
||
| log.info(scrapeResultPaths); | ||
| const { | ||
| seoChecks, | ||
| detectedTags, | ||
| extractedTags, | ||
| } = await metatagsAutoDetect(site, scrapeResultPaths, context); | ||
|
|
||
| // Calculate projected traffic lost | ||
| const { | ||
|
|
@@ -355,6 +326,6 @@ export async function submitForScraping(context) { | |
| export default new AuditBuilder() | ||
| .withUrlResolver((site) => site.getBaseURL()) | ||
| .addStep('submit-for-import-top-pages', importTopPages, AUDIT_STEP_DESTINATIONS.IMPORT_WORKER) | ||
| .addStep('submit-for-scraping', submitForScraping, AUDIT_STEP_DESTINATIONS.SCRAPE_CLIENT) | ||
| .addStep('run-audit-and-generate-suggestions', runAuditAndGenerateSuggestions) | ||
| .build(); | ||
This file contains hidden or 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
This file contains hidden or 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
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.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
This check was added since the home page had no path(empty). Will the page url being computed above be '/' for home page now?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
new URL(url).pathnamewill resolve to'/'for the home page