add Business Insider

Author: MaxDall

docs/supported_publishers.md

@@ -78,6 +78,21 @@
       <td>&#160;</td>
       <td>&#160;</td>
     </tr>
+    <tr>
+      <td>
+        <code>BusinessInsider</code>
+      </td>
+      <td>
+        <div>Business Insider</div>
+      </td>
+      <td>
+        <a href="https://www.businessinsider.de/">
+          <span>www.businessinsider.de</span>
+        </a>
+      </td>
+      <td>&#160;</td>
+      <td>&#160;</td>
+    </tr>
     <tr>
       <td>
         <code>DW</code>

src/fundus/publishers/de/__init__.py

@@ -6,6 +6,7 @@
 
 from .berliner_zeitung import BerlinerZeitungParser
 from .bild import BildParser
+from .business_insider import BusinessInsiderParser
 from .die_welt import DieWeltParser
 from .die_zeit import DieZeitParser
 from .dw import DWParser
@@ -190,3 +191,13 @@ class DE(PublisherEnum):
         sources=[NewsMap("https://www.waz.de/sitemaps/news.xml")],
         parser=WAZParser,
     )
+
+    BusinessInsider = PublisherSpec(
+        name="Business Insider",
+        domain="https://www.businessinsider.de/",
+        sources=[
+            NewsMap("https://www.businessinsider.de/news-sitemap.xml"),
+            Sitemap("https://www.businessinsider.de/sitemap_index.xml"),
+        ],
+        parser=BusinessInsiderParser,
+    )

src/fundus/publishers/de/business_insider.py

@@ -0,0 +1,50 @@
+import datetime
+from typing import List, Optional
+
+from lxml.cssselect import CSSSelector
+from lxml.etree import XPath
+
+from fundus.parser import ArticleBody, BaseParser, ParserProxy, attribute
+from fundus.parser.utility import (
+    extract_article_body_with_selector,
+    generic_author_parsing,
+    generic_date_parsing,
+    generic_topic_parsing,
+)
+
+
+class BusinessInsiderParser(ParserProxy):
+    class V1(BaseParser):
+        _summary_selector = CSSSelector("article div.bi-bulletpoints > p")
+        _subheadline_selector = CSSSelector("article h2")
+
+        # The mark is to remove prepended text about machine translation
+        _paragraph_selector = XPath(
+            "//article //div[contains(@class, 'article-body')] "
+            "/p[not(mark[@class='has-inline-color has-cyan-bluish-gray-color'])]"
+        )
+
+        @attribute
+        def body(self) -> ArticleBody:
+            return extract_article_body_with_selector(
+                self.precomputed.doc,
+                summary_selector=self._summary_selector,
+                subheadline_selector=self._subheadline_selector,
+                paragraph_selector=self._paragraph_selector,
+            )
+
+        @attribute
+        def authors(self) -> List[str]:
+            return generic_author_parsing(self.precomputed.ld.bf_search("author"))
+
+        @attribute
+        def publishing_date(self) -> Optional[datetime.datetime]:
+            return generic_date_parsing(self.precomputed.ld.bf_search("datePublished"))
+
+        @attribute
+        def title(self) -> Optional[str]:
+            return self.precomputed.ld.bf_search("headline")
+
+        @attribute
+        def topics(self) -> List[str]:
+            return generic_topic_parsing(self.precomputed.meta.get("keywords"))

tests/resources/parser/test_data/de/BusinessInsider.json

@@ -0,0 +1,15 @@
+{
+  "V1": {
+    "authors": [
+      "Matthew Loh"
+    ],
+    "publishing_date": "2024-01-29 19:00:45+00:00",
+    "title": "Wie groß ist Evergrande, Chinas strauchelnder Immobilienriese?",
+    "topics": [
+      "China",
+      "Immobilien",
+      "Pleite",
+      "Schulden"
+    ]
+  }
+}

tests/resources/parser/test_data/de/BusinessInsider_2024_01_29.html.gz

@@ -7,6 +7,10 @@
     "url": "https://www.bild.de/sport/fussball/fortuna-duesseldorf/bubi-bomber-wieder-da-thioune-fordert-geduld-mit-niemiec-83936220.bild.html",
     "crawl_date": "2023-05-15 13:55:04.823203"
   },
+  "BusinessInsider_2024_01_29.html.gz": {
+    "url": "https://www.businessinsider.de/wirtschaft/international-business/wie-gross-ist-evergrande-chinas-sterbender-immobilienriese/",
+    "crawl_date": "2024-01-29 22:53:02.986279"
+  },
   "DW_2023_04_28.html.gz": {
     "url": "https://www.dw.com/de/ukrainische-gegenoffensive-ziele-chancen-risiken/a-65464327?maca=de-rss-de-all-1119-xml-mrss",
     "crawl_date": "2023-04-28 20:25:18.143350"