Fix a bunch of BeautifulSoup deprecation warnings

Refs https://github.com/simonw/datasette/issues/2461#issuecomment-2635156004
pull/2464/head
Simon Willison 2025-02-04 13:56:17 -08:00
rodzic 11433e40b3
commit 6d247005ae
5 zmienionych plików z 39 dodań i 39 usunięć

Wyświetl plik

@ -45,7 +45,7 @@ def test_homepage(app_client_two_attached_databases):
)
# We should only show visible, not hidden tables here:
table_links = [
{"href": a["href"], "text": a.text.strip()} for a in links_p.findAll("a")
{"href": a["href"], "text": a.text.strip()} for a in links_p.find_all("a")
]
assert [
{"href": r"/extra+database/searchable_fts", "text": "searchable_fts"},
@ -226,7 +226,7 @@ def test_row_page_does_not_truncate():
assert table["class"] == ["rows-and-columns"]
assert ["Mission"] == [
td.string
for td in table.findAll("td", {"class": "col-neighborhood-b352a7"})
for td in table.find_all("td", {"class": "col-neighborhood-b352a7"})
]
@ -242,7 +242,7 @@ def test_query_page_truncates():
)
assert response.status_code == 200
table = Soup(response.content, "html.parser").find("table")
tds = table.findAll("td")
tds = table.find_all("td")
assert [str(td) for td in tds] == [
'<td class="col-a">this …</td>',
'<td class="col-b"><a href="https://example.com/">http…</a></td>',
@ -407,7 +407,7 @@ async def test_row_links_from_other_tables(
soup = Soup(response.text, "html.parser")
h2 = soup.find("h2")
assert h2.text == "Links from other tables"
li = h2.findNext("ul").find("li")
li = h2.find_next("ul").find("li")
text = re.sub(r"\s+", " ", li.text.strip())
assert text == expected_text
link = li.find("a")["href"]
@ -501,7 +501,7 @@ def test_database_download_for_immutable():
# Regular page should have a download link
response = client.get("/fixtures")
soup = Soup(response.content, "html.parser")
assert len(soup.findAll("a", {"href": re.compile(r"\.db$")}))
assert len(soup.find_all("a", {"href": re.compile(r"\.db$")}))
# Check we can actually download it
download_response = client.get("/fixtures.db")
assert download_response.status_code == 200
@ -530,7 +530,7 @@ def test_database_download_disallowed_for_mutable(app_client):
# Use app_client because we need a file database, not in-memory
response = app_client.get("/fixtures")
soup = Soup(response.content, "html.parser")
assert len(soup.findAll("a", {"href": re.compile(r"\.db$")})) == 0
assert len(soup.find_all("a", {"href": re.compile(r"\.db$")})) == 0
assert app_client.get("/fixtures.db").status_code == 403
@ -539,7 +539,7 @@ def test_database_download_disallowed_for_memory():
# Memory page should NOT have a download link
response = client.get("/_memory")
soup = Soup(response.content, "html.parser")
assert 0 == len(soup.findAll("a", {"href": re.compile(r"\.db$")}))
assert 0 == len(soup.find_all("a", {"href": re.compile(r"\.db$")}))
assert 404 == client.get("/_memory.db").status
@ -549,7 +549,7 @@ def test_allow_download_off():
) as client:
response = client.get("/fixtures")
soup = Soup(response.content, "html.parser")
assert not len(soup.findAll("a", {"href": re.compile(r"\.db$")}))
assert not len(soup.find_all("a", {"href": re.compile(r"\.db$")}))
# Accessing URL directly should 403
response = client.get("/fixtures.db")
assert 403 == response.status
@ -559,7 +559,7 @@ def test_allow_sql_off():
with make_app_client(config={"allow_sql": {}}) as client:
response = client.get("/fixtures")
soup = Soup(response.content, "html.parser")
assert not len(soup.findAll("textarea", {"name": "sql"}))
assert not len(soup.find_all("textarea", {"name": "sql"}))
# The table page should no longer show "View and edit SQL"
response = client.get("/fixtures/sortable")
assert b"View and edit SQL" not in response.content
@ -855,7 +855,7 @@ def test_base_url_config(app_client_base_url_prefix, path, use_prefix):
soup = Soup(response.content, "html.parser")
for form in soup.select("form"):
assert form["action"].startswith("/prefix")
for el in soup.findAll(["a", "link", "script"]):
for el in soup.find_all(["a", "link", "script"]):
if "href" in el.attrs:
href = el["href"]
elif "src" in el.attrs:

Wyświetl plik

@ -390,7 +390,7 @@ async def test_permissions_debug(ds_client, filter_):
assert fragment in response.text
# Should show one failure and one success
soup = Soup(response.text, "html.parser")
check_divs = soup.findAll("div", {"class": "check"})
check_divs = soup.find_all("div", {"class": "check"})
checks = [
{
"action": div.select_one(".check-action").text,

Wyświetl plik

@ -113,7 +113,7 @@ async def test_hook_plugin_prepare_connection_arguments(ds_client):
async def test_hook_extra_css_urls(ds_client, path, expected_decoded_object):
response = await ds_client.get(path)
assert response.status_code == 200
links = Soup(response.text, "html.parser").findAll("link")
links = Soup(response.text, "html.parser").find_all("link")
special_href = [
link
for link in links
@ -128,7 +128,7 @@ async def test_hook_extra_css_urls(ds_client, path, expected_decoded_object):
@pytest.mark.asyncio
async def test_hook_extra_js_urls(ds_client):
response = await ds_client.get("/")
scripts = Soup(response.text, "html.parser").findAll("script")
scripts = Soup(response.text, "html.parser").find_all("script")
script_attrs = [s.attrs for s in scripts]
for attrs in [
{
@ -153,7 +153,7 @@ async def test_plugins_with_duplicate_js_urls(ds_client):
# What matters is that https://plugin-example.datasette.io/jquery.js is only there once
# and it comes before plugin1.js and plugin2.js which could be in either
# order
scripts = Soup(response.text, "html.parser").findAll("script")
scripts = Soup(response.text, "html.parser").find_all("script")
srcs = [s["src"] for s in scripts if s.get("src")]
# No duplicates allowed:
assert len(srcs) == len(set(srcs))
@ -541,7 +541,7 @@ async def test_hook_register_output_renderer_can_render(ds_client):
links = (
Soup(response.text, "html.parser")
.find("p", {"class": "export-links"})
.findAll("a")
.find_all("a")
)
actual = [link["href"] for link in links]
# Should not be present because we sent ?_no_can_render=1

Wyświetl plik

@ -68,13 +68,13 @@ def test_table_cell_truncation():
"Arcad…",
] == [
td.string
for td in table.findAll("td", {"class": "col-neighborhood-b352a7"})
for td in table.find_all("td", {"class": "col-neighborhood-b352a7"})
]
# URLs should be truncated too
response2 = client.get("/fixtures/roadside_attractions")
assert response2.status == 200
table = Soup(response2.body, "html.parser").find("table")
tds = table.findAll("td", {"class": "col-url"})
tds = table.find_all("td", {"class": "col-url"})
assert [str(td) for td in tds] == [
'<td class="col-url type-str"><a href="https://www.mysteryspot.com/">http…</a></td>',
'<td class="col-url type-str"><a href="https://winchestermysteryhouse.com/">http…</a></td>',
@ -210,7 +210,7 @@ async def test_searchable_view_persists_fts_table(ds_client):
response = await ds_client.get(
"/fixtures/searchable_view?_fts_table=searchable_fts&_fts_pk=pk"
)
inputs = Soup(response.text, "html.parser").find("form").findAll("input")
inputs = Soup(response.text, "html.parser").find("form").find_all("input")
hiddens = [i for i in inputs if i["type"] == "hidden"]
assert [("_fts_table", "searchable_fts"), ("_fts_pk", "pk")] == [
(hidden["name"], hidden["value"]) for hidden in hiddens
@ -234,7 +234,7 @@ async def test_sort_by_desc_redirects(ds_client):
async def test_sort_links(ds_client):
response = await ds_client.get("/fixtures/sortable?_sort=sortable")
assert response.status_code == 200
ths = Soup(response.text, "html.parser").findAll("th")
ths = Soup(response.text, "html.parser").find_all("th")
attrs_and_link_attrs = [
{
"attrs": th.attrs,
@ -341,7 +341,7 @@ async def test_facet_display(ds_client):
)
assert response.status_code == 200
soup = Soup(response.text, "html.parser")
divs = soup.find("div", {"class": "facet-results"}).findAll("div")
divs = soup.find("div", {"class": "facet-results"}).find_all("div")
actual = []
for div in divs:
actual.append(
@ -353,7 +353,7 @@ async def test_facet_display(ds_client):
"qs": a["href"].split("?")[-1],
"count": int(str(a.parent).split("</a>")[1].split("<")[0]),
}
for a in div.find("ul").findAll("a")
for a in div.find("ul").find_all("a")
],
}
)
@ -422,7 +422,7 @@ async def test_facets_persist_through_filter_form(ds_client):
"/fixtures/facetable?_facet=planet_int&_facet=_city_id&_facet_array=tags"
)
assert response.status_code == 200
inputs = Soup(response.text, "html.parser").find("form").findAll("input")
inputs = Soup(response.text, "html.parser").find("form").find_all("input")
hiddens = [i for i in inputs if i["type"] == "hidden"]
assert [(hidden["name"], hidden["value"]) for hidden in hiddens] == [
("_facet", "planet_int"),
@ -435,7 +435,7 @@ async def test_facets_persist_through_filter_form(ds_client):
async def test_next_does_not_persist_in_hidden_field(ds_client):
response = await ds_client.get("/fixtures/searchable?_size=1&_next=1")
assert response.status_code == 200
inputs = Soup(response.text, "html.parser").find("form").findAll("input")
inputs = Soup(response.text, "html.parser").find("form").find_all("input")
hiddens = [i for i in inputs if i["type"] == "hidden"]
assert [(hidden["name"], hidden["value"]) for hidden in hiddens] == [
("_size", "1"),
@ -448,7 +448,7 @@ async def test_table_html_simple_primary_key(ds_client):
assert response.status_code == 200
table = Soup(response.text, "html.parser").find("table")
assert table["class"] == ["rows-and-columns"]
ths = table.findAll("th")
ths = table.find_all("th")
assert "id\xa0" == ths[0].find("a").string.strip()
for expected_col, th in zip(("content",), ths[1:]):
a = th.find("a")
@ -479,7 +479,7 @@ async def test_table_csv_json_export_interface(ds_client):
links = (
Soup(response.text, "html.parser")
.find("p", {"class": "export-links"})
.findAll("a")
.find_all("a")
)
actual = [link["href"] for link in links]
expected = [
@ -493,7 +493,7 @@ async def test_table_csv_json_export_interface(ds_client):
assert expected == actual
# And the advanced export box at the bottom:
div = Soup(response.text, "html.parser").find("div", {"class": "advanced-export"})
json_links = [a["href"] for a in div.find("p").findAll("a")]
json_links = [a["href"] for a in div.find("p").find_all("a")]
assert [
"/fixtures/simple_primary_key.json?id__gt=2",
"/fixtures/simple_primary_key.json?id__gt=2&_shape=array",
@ -503,7 +503,7 @@ async def test_table_csv_json_export_interface(ds_client):
# And the CSV form
form = div.find("form")
assert form["action"].endswith("/simple_primary_key.csv")
inputs = [str(input) for input in form.findAll("input")]
inputs = [str(input) for input in form.find_all("input")]
assert [
'<input name="_dl" type="checkbox"/>',
'<input type="submit" value="Export CSV"/>',
@ -519,7 +519,7 @@ async def test_csv_json_export_links_include_labels_if_foreign_keys(ds_client):
links = (
Soup(response.text, "html.parser")
.find("p", {"class": "export-links"})
.findAll("a")
.find_all("a")
)
actual = [link["href"] for link in links]
expected = [
@ -571,7 +571,7 @@ async def test_rowid_sortable_no_primary_key(ds_client):
assert response.status_code == 200
table = Soup(response.text, "html.parser").find("table")
assert table["class"] == ["rows-and-columns"]
ths = table.findAll("th")
ths = table.find_all("th")
assert "rowid\xa0" == ths[1].find("a").string.strip()
@ -580,7 +580,7 @@ async def test_table_html_compound_primary_key(ds_client):
response = await ds_client.get("/fixtures/compound_primary_key")
assert response.status_code == 200
table = Soup(response.text, "html.parser").find("table")
ths = table.findAll("th")
ths = table.find_all("th")
assert "Link" == ths[0].string.strip()
for expected_col, th in zip(("pk1", "pk2", "content"), ths[1:]):
a = th.find("a")
@ -811,7 +811,7 @@ async def test_advanced_export_box(ds_client, path, has_object, has_stream, has_
if has_object:
expected_json_shapes.append("object")
div = soup.find("div", {"class": "advanced-export"})
assert expected_json_shapes == [a.text for a in div.find("p").findAll("a")]
assert expected_json_shapes == [a.text for a in div.find("p").find_all("a")]
# "stream all rows" option
if has_stream:
assert "stream all rows" in str(div)
@ -828,13 +828,13 @@ async def test_extra_where_clauses(ds_client):
soup = Soup(response.text, "html.parser")
div = soup.select(".extra-wheres")[0]
assert "2 extra where clauses" == div.find("h3").text
hrefs = [a["href"] for a in div.findAll("a")]
hrefs = [a["href"] for a in div.find_all("a")]
assert [
"/fixtures/facetable?_where=_city_id%3D1",
"/fixtures/facetable?_where=_neighborhood%3D%27Dogpatch%27",
] == hrefs
# These should also be persisted as hidden fields
inputs = soup.find("form").findAll("input")
inputs = soup.find("form").find_all("input")
hiddens = [i for i in inputs if i["type"] == "hidden"]
assert [("_where", "_neighborhood='Dogpatch'"), ("_where", "_city_id=1")] == [
(hidden["name"], hidden["value"]) for hidden in hiddens
@ -859,7 +859,7 @@ async def test_extra_where_clauses(ds_client):
async def test_other_hidden_form_fields(ds_client, path, expected_hidden):
response = await ds_client.get(path)
soup = Soup(response.text, "html.parser")
inputs = soup.find("form").findAll("input")
inputs = soup.find("form").find_all("input")
hiddens = [i for i in inputs if i["type"] == "hidden"]
assert [(hidden["name"], hidden["value"]) for hidden in hiddens] == expected_hidden
@ -878,7 +878,7 @@ async def test_search_and_sort_fields_not_duplicated(ds_client, path, expected_h
# https://github.com/simonw/datasette/issues/1214
response = await ds_client.get(path)
soup = Soup(response.text, "html.parser")
inputs = soup.find("form").findAll("input")
inputs = soup.find("form").find_all("input")
hiddens = [i for i in inputs if i["type"] == "hidden"]
assert [(hidden["name"], hidden["value"]) for hidden in hiddens] == expected_hidden
@ -960,7 +960,7 @@ async def test_metadata_sort(ds_client):
assert response.status_code == 200
table = Soup(response.text, "html.parser").find("table")
assert table["class"] == ["rows-and-columns"]
ths = table.findAll("th")
ths = table.find_all("th")
assert ["id", "name\xa0"] == [th.find("a").string.strip() for th in ths]
rows = [[str(td) for td in tr.select("td")] for tr in table.select("tbody tr")]
expected = [
@ -996,7 +996,7 @@ async def test_metadata_sort_desc(ds_client):
assert response.status_code == 200
table = Soup(response.text, "html.parser").find("table")
assert table["class"] == ["rows-and-columns"]
ths = table.findAll("th")
ths = table.find_all("th")
assert ["pk\xa0", "name"] == [th.find("a").string.strip() for th in ths]
rows = [[str(td) for td in tr.select("td")] for tr in table.select("tbody tr")]
expected = [
@ -1098,7 +1098,7 @@ async def test_column_metadata(ds_client):
response = await ds_client.get("/fixtures/roadside_attractions")
soup = Soup(response.text, "html.parser")
dl = soup.find("dl")
assert [(dt.text, dt.nextSibling.text) for dt in dl.findAll("dt")] == [
assert [(dt.text, dt.nextSibling.text) for dt in dl.find_all("dt")] == [
("address", "The street address for the attraction"),
("name", "The name of the attraction"),
]

Wyświetl plik

@ -7,7 +7,7 @@ def last_event(datasette):
def assert_footer_links(soup):
footer_links = soup.find("footer").findAll("a")
footer_links = soup.find("footer").find_all("a")
assert 4 == len(footer_links)
datasette_link, license_link, source_link, about_link = footer_links
assert "Datasette" == datasette_link.text.strip()