Fix compatibility with newer lxml versions

freelawproject · Jan 8, 2024 · 73c2c3c · 73c2c3c
1 parent ee46665
commit 73c2c3c
Show file tree

Hide file tree

Showing 3 changed files with 6 additions and 3 deletions.
diff --git a/juriscraper/lib/html_utils.py b/juriscraper/lib/html_utils.py
@@ -51,7 +51,8 @@ def get_html5_parsed_text(text: str) -> HtmlElement:
     :param text: The html of the document
     :return: an lxml.HtmlElement object
     """
-    parsed = html5parser.document_fromstring(text)
+    parser = html5parser.HTMLParser(namespaceHTMLElements=False)
+    parsed = html5parser.document_fromstring(text, parser=parser)
     return fromstring(tostring(parsed, encoding="unicode"))
 
 

diff --git a/juriscraper/pacer/claims_register.py b/juriscraper/pacer/claims_register.py
@@ -84,7 +84,9 @@ def metadata(self):
 
         # Each cell in the header table has a value like:
         # <td><b>Judge:</b>  Barbara J. Houser</td>
-        cells = self.tree.xpath("//center/p/table[1]//td[text()]")
+        cells = self.tree.xpath(
+            "//center/p/following-sibling::table[1]//td[text()]"
+        )
         for cell in cells:
             label_node = cell.xpath("./b")[0]
             data.update(

diff --git a/requirements.txt b/requirements.txt
@@ -7,7 +7,7 @@ dateparser>=1.2.0
 feedparser>=6.0.11
 geonamescache>=2.0.0
 html5lib
-lxml~=4.9
+lxml>=4.9
 python-dateutil>=2.8.2
 requests>=2.20.0
 selenium>=4.9.1