feat(crawler): sync local data

This commit is contained in:
2025-11-14 14:31:32 +02:00
parent 4ec2a608b1
commit 05a78913c0
9 changed files with 81 additions and 75 deletions
+10 -19
View File
@@ -5,16 +5,13 @@
"paginationTemplate": "actualite",
"requiresDetails": true,
"requiresRateLimit": false,
"sourceDate": {
"pattern": "/(\\d{2})/(\\d{2})/(\\d{4}) - (\\d{2}:\\d{2})/",
"replacement": "$3-$2-$1 $4"
},
"sourceDate": {},
"sourceId": "radiookapi.net",
"sourceKind": "html",
"sourceSelectors": {
"articleBody": ".field-name-body",
"articleCategories": ".views-field-field-cat-gorie a",
"articleDate": ".views-field-created",
"articleDate": "head > meta[property=\"article:published_time\"]",
"articleLink": ".views-field-title a",
"articles": ".view-content > .views-row.content-row",
"articleTitle": "h1.page-header",
@@ -26,17 +23,14 @@
{
"categories": ["politique", "economie", "culture", "sport", "societe"],
"paginationTemplate": "index.php/category/{category}",
"requiresDetails": false,
"requiresDetails": true,
"requiresRateLimit": false,
"sourceDate": {
"pattern": "/\\w{3} (\\d{2})/(\\d{2})/(\\d{4}) - (\\d{2}:\\d{2})/",
"replacement": "$3-$2-$1 $4"
},
"sourceDate": {},
"sourceId": "7sur7.cd",
"sourceKind": "html",
"sourceSelectors": {
"articleBody": ".field.field--name-body",
"articleDate": ".views-field-created",
"articleBody": "div[property=\"schema:text\"].field.field--name-body",
"articleDate": "head > meta[property=\"article:published_time\"]",
"articleLink": ".views-field-title a",
"articles": ".view-content > .row.views-row",
"articleTitle": ".views-field-title a",
@@ -50,7 +44,7 @@
"requiresDetails": true,
"requiresRateLimit": false,
"sourceDate": {
"format": "%d.%m.%Y %H:%M"
"format": "dd.MM.yyyy"
},
"sourceId": "mediacongo.net",
"sourceKind": "html",
@@ -70,16 +64,13 @@
"paginationTemplate": "actualite",
"requiresDetails": true,
"requiresRateLimit": false,
"sourceDate": {
"pattern": "/(\\d{1}) (\\d{1,2}) (\\d{2}) (\\d{4}) - (\\d{2}:\\d{2})/",
"replacement": "$4-$3-$2 $5"
},
"sourceDate": {},
"sourceId": "actualite.cd",
"sourceKind": "html",
"sourceSelectors": {
"articleBody": ".views-field.views-field-body",
"articleBody": ".views-field.views-field-body .field-content",
"articleCategories": "#actu-cat",
"articleDate": "#p-date",
"articleDate": "head > meta[property=\"article:published_time\"]",
"articleLink": "#actu-titre a",
"articles": "#views-bootstrap-taxonomy-term-page-2 > div > div",
"articleTitle": "h1.page-title"