MAINT: remove deprecated usage of BeautifulSoup

bsipocz · bsipocz · commit bafbef83866c · 2024-06-14T18:41:38.000-07:00
diff --git a/astroquery/alma/core.py b/astroquery/alma/core.py
@@ -1162,9 +1162,9 @@ def _cycle0_tarfile_content(self):
             # <tr width="blah"> which the default parser does not pick up
             root = BeautifulSoup(response.content, 'html.parser')
             html_table = root.find('table', class_='grid listing')
-            data = list(zip(*[(x.findAll('td')[0].text,
-                               x.findAll('td')[1].text)
-                              for x in html_table.findAll('tr')]))
+            data = list(zip(*[(x.find_all('td')[0].text,
+                               x.find_all('td')[1].text)
+                              for x in html_table.find_all('tr')]))
             columns = [Column(data=data[0], name='ID'),
                        Column(data=data[1], name='Files')]
             tbl = Table(columns)
diff --git a/astroquery/cosmosim/core.py b/astroquery/cosmosim/core.py
@@ -1109,7 +1109,7 @@ def download(self, jobid=None, filename=None, format=None, cache=True):
                     auth=(self.username, self.password))
                 soup = BeautifulSoup(results.content, "lxml")
                 urls = [i.get('xlink:href')
-                        for i in soup.findAll({'uws:result'})]
+                        for i in soup.find_all({'uws:result'})]
                 formatlist = [urls[i].split('/')[-1].upper()
                               for i in range(len(urls))]
 
diff --git a/astroquery/eso/core.py b/astroquery/eso/core.py
@@ -348,10 +348,10 @@ def list_surveys(self, *, cache=True):
             collections_table = root.find('table', id='collections_table')
             other_collections = root.find('select', id='collection_name_option')
             # it is possible to have empty collections or other collections...
-            collection_elts = (collections_table.findAll('input', type='checkbox')
+            collection_elts = (collections_table.find_all('input', type='checkbox')
                                if collections_table is not None
                                else [])
-            other_elts = (other_collections.findAll('option')
+            other_elts = (other_collections.find_all('option')
                           if other_collections is not None
                           else [])
             for element in (collection_elts + other_elts):
@@ -969,7 +969,7 @@ def _print_surveys_help(self, url, *, cache=True):
 
         # hovertext from different labels are used to give more info on forms
         helptext_dict = {abbr['title'].split(":")[0].strip(): ":".join(abbr['title'].split(":")[1:])
-                         for abbr in form.findAll('abbr')
+                         for abbr in form.find_all('abbr')
                          if 'title' in abbr.attrs and ":" in abbr['title']}
 
         for fieldset in form.select('fieldset'):
diff --git a/astroquery/ipac/irsa/ibe/core.py b/astroquery/ipac/irsa/ibe/core.py
@@ -271,7 +271,7 @@ def list_missions(self, *, cache=True):
                                      cache=cache)
 
             root = BeautifulSoup(response.text, 'html5lib')
-            links = root.findAll('a')
+            links = root.find_all('a')
 
             missions = [os.path.basename(a.attrs['href'].rstrip('/')) for a in links]
             self._missions = missions
@@ -309,7 +309,7 @@ def list_datasets(self, *, mission=None, cache=True):
                                  cache=cache)
 
         root = BeautifulSoup(response.text, 'html5lib')
-        links = root.findAll('a')
+        links = root.find_all('a')
         datasets = [a.text for a in links
                     if a.attrs['href'].count('/') >= 4  # shown as '..'; ignore
                     ]
@@ -364,7 +364,7 @@ def list_tables(self, *, mission=None, dataset=None, cache=True):
                                  cache=cache)
 
         root = BeautifulSoup(response.text, 'html5lib')
-        return [tr.find('td').string for tr in root.findAll('tr')[1:]]
+        return [tr.find('td').string for tr in root.find_all('tr')[1:]]
 
     # Unfortunately, the URL construction for each data set is different, and
     # they're not obviously accessible via API
diff --git a/astroquery/linelists/cdms/core.py b/astroquery/linelists/cdms/core.py
@@ -156,7 +156,7 @@ def query_lines_async(self, min_frequency, max_frequency, *,
         soup = BeautifulSoup(response.text, 'html.parser')
 
         ok = False
-        urls = [x.attrs['src'] for x in soup.findAll('frame',)]
+        urls = [x.attrs['src'] for x in soup.find_all('frame',)]
         for url in urls:
             if 'tab' in url and 'head' not in url:
                 ok = True
diff --git a/astroquery/simbad/get_votable_fields.py b/astroquery/simbad/get_votable_fields.py
@@ -17,7 +17,7 @@ def reload_votable_fields_json():
     # Find the first <table> tag that follows it
     table = foundtext.findNext('table')
     outd = {}
-    for row in table.findAll('tr'):
+    for row in table.find_all('tr'):
         cols = row.findChildren('td')
         if len(cols) > 1:
             smallest_child = cols[0].find_all()[-1]
diff --git a/astroquery/skyview/core.py b/astroquery/skyview/core.py
@@ -283,10 +283,10 @@ def survey_dict(self):
             response = self._request('GET', self.URL, cache=False)
             response.raise_for_status()
             page = BeautifulSoup(response.content, "html.parser")
-            surveys = page.findAll('select', {'name': 'survey'})
+            surveys = page.find_all('select', {'name': 'survey'})
 
             self._survey_dict = {
-                sel['id']: [x.text for x in sel.findAll('option')]
+                sel['id']: [x.text for x in sel.find_all('option')]
                 for sel in surveys
                 if 'overlay' not in sel['id']
             }
diff --git a/astroquery/splatalogue/build_species_table.py b/astroquery/splatalogue/build_species_table.py
@@ -53,7 +53,7 @@ def get_json_species_ids(*, outfile='splat-species.json', base_url=conf.base_url
     result = requests.get(f'{base_url}/b.php')
     page = bs4.BeautifulSoup(result.content, 'html5lib')
     # The ID needs to be checked periodically if Splatalogue is updated
-    sid = page.findAll('select', attrs={'id': 'speciesselectbox'})[0]
+    sid = page.find_all('select', attrs={'id': 'speciesselectbox'})[0]
 
     species_types = set()
     for kid in sid.children:
diff --git a/astroquery/wfau/core.py b/astroquery/wfau/core.py
@@ -665,7 +665,7 @@ def _get_databases(self):
 
         root = BeautifulSoup(response.content, features='html5lib')
         databases = [xrf.attrs['value'] for xrf in
-                     root.find('select').findAll('option')]
+                     root.find('select').find_all('option')]
         return databases
 
     def list_databases(self):
