PLQ : pages d'amorçage médias, documents officiels, valeurs
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
1 changed file +3 −2
modified
engine/qc26/connectors/parties/documents.py
+3 −2
@@ -62,7 +62,8 @@ SITES: dict[str, PartySite] = { | |||||
| 62 | ("plateforme 2026", "engagements", "cadre financier", "communiqué de presse"), | 62 | ("plateforme 2026", "engagements", "cadre financier", "communiqué de presse"), | ||
| 63 | re.compile(r"plq\.org/(?!.*(don|boutique|adhesion|nous-joindre|recherche|logo))", re.I), | 63 | re.compile(r"plq\.org/(?!.*(don|boutique|adhesion|nous-joindre|recherche|logo))", re.I), | ||
| 64 | re.compile(r"(\.(jpg|jpeg|png|gif|svg|webp|mp4)|/en/|/page/\d|wp-json|/feed|#)", re.I), | 64 | re.compile(r"(\.(jpg|jpeg|png|gif|svg|webp|mp4)|/en/|/page/\d|wp-json|/feed|#)", re.I), | ||
| 65 | − ("https://plq.org/", "https://plq.org/engagements", "https://plq.org/communiques", "https://plq.org/fr/communiques", "https://plq.org/fr/nouvelles/", "https://plq.org/fr/plateforme/")), | 65 | + ("https://plq.org/", "https://plq.org/engagements", "https://plq.org/medias/", "https://plq.org/documents-officiels/", "https://plq.org/nos-valeurs-liberales/", | ||
| 66 | + "https://plq.org/communiques", "https://plq.org/fr/communiques", "https://plq.org/fr/nouvelles/", "https://plq.org/fr/plateforme/")), | ||||
| 66 | "pq": PartySite("pq", "https://pq.org/", | 67 | "pq": PartySite("pq", "https://pq.org/", | ||
| 67 | ("programme", "plateforme électorale 2026", "engagements", "cadre financier", "communiqué"), | 68 | ("programme", "plateforme électorale 2026", "engagements", "cadre financier", "communiqué"), | ||
| 68 | re.compile(r"pq\.org/(?!.*(don|boutique|adhesion|ressources|nous-joindre|recherche))", re.I), | 69 | re.compile(r"pq\.org/(?!.*(don|boutique|adhesion|ressources|nous-joindre|recherche))", re.I), | ||
@@ -103,7 +104,7 @@ def classify_doc_type(url: str, title: str | None) -> str: | |||||
| 103 | return "page" | 104 | return "page" | ||
| 104 | 105 | ||||
| 105 | 106 | ||||
| 106 | −CONTENT_RE = re.compile(r"(plateforme|programme|engagement|priorit|cadre|vision|propos|promesse|plan|mesure|projet|nouvelles?/|actualit|communique|blog/ressources|declaration|\.pdf)", re.I) | 107 | +CONTENT_RE = re.compile(r"(plateforme|programme|engagement|priorit|cadre|vision|propos|promesse|plan|mesure|projet|nouvelles?/|actualit|communique|blog/ressources|declaration|medias/|documents-officiels|valeurs|\.pdf)", re.I) | ||
| 107 | 108 | ||||
| 108 | 109 | ||||
| 109 | def _page_links(url: str, site: PartySite) -> tuple[list[str], str]: | 110 | def _page_links(url: str, site: PartySite) -> tuple[list[str], str]: | ||
| 110 | 111 | ||||