add regex to paragraph selector

MaxDall · MaxDall · commit a9c44e2fae49 · 2024-02-12T14:46:29.000+01:00
diff --git a/src/fundus/publishers/de/dw.py b/src/fundus/publishers/de/dw.py
@@ -23,7 +23,7 @@ class V2(BaseParser):
         # https://regex101.com/r/uZLwyb/1
         _author_regex = r"^([a-z]{2,3}\/|[A-Z]{2,3}\/)*([a-z]{2,3}|[A-Z]{2,3})\s\(([a-z]{2,3}, )*([a-z]{2,3})\)$"
         _paragraph_selector = XPath(
-            f"//div[contains(@class, 'rich-text')] /p[not(em) or text() and not(re:test(text(), '{_author_regex}'))]",
+            f"//div[contains(@class, 'rich-text')] /p[text() and not(re:test(text(), '{_author_regex}'))]",
             namespaces={"re": "http://exslt.org/regular-expressions"},
         )
         _summary_selector = CSSSelector("header > p")

Original file line number	Diff line number	Diff line change
`@@ -23,7 +23,7 @@ class V2(BaseParser):`
`23`	`23`	`# https://regex101.com/r/uZLwyb/1`
`24`	`24`	`_author_regex = r"^([a-z]{2,3}\/\|[A-Z]{2,3}\/)([a-z]{2,3}\|[A-Z]{2,3})\s\(([a-z]{2,3}, )([a-z]{2,3})\)$"`
`25`	`25`	`_paragraph_selector = XPath(`
`26`		`- f"//div[contains(@class, 'rich-text')] /p[not(em) or text() and not(re:test(text(), '{_author_regex}'))]",`
	`26`	`+ f"//div[contains(@class, 'rich-text')] /p[text() and not(re:test(text(), '{_author_regex}'))]",`
`27`	`27`	`namespaces={"re": "http://exslt.org/regular-expressions"},`
`28`	`28`	`)`
`29`	`29`	`_summary_selector = CSSSelector("header > p")`