+ |
+ What's new in Python 2.7?
+ or all "What's new" documents since 2.0
+ Tutorial
+ start here
+ Library Reference
+ keep this under your pillow
+ Language Reference
+ describes syntax and language elements
+ Python Setup and Usage
+ how to use Python on different platforms
+ Python HOWTOs
+ in-depth documents on specific topics
+ |
+ Installing Python Modules
+ installing from the Python Package Index & other sources
+ Distributing Python Modules
+ publishing modules for installation by others
+ Extending and Embedding
+ tutorial for C/C++ programmers
+ Python/C API
+ reference for C/C++ programmers
+ FAQs
+ frequently asked questions (with answers!)
+ |
+
+
+
+ |
+ Python Global Module Index
+ quick access to all modules
+ General Index
+ all functions, classes, terms
+ Glossary
+ the most important terms explained
+ |
+ Search page
+ search this documentation
+ Complete Table of Contents
+ lists all sections and subsections
+ |
+
+ """ # noqa: E501
+
@pytest.mark.network
- @tm.network(url="https://docs.python.org/2/", check_before_test=True)
- def test_multiple_matches(self):
- url = "https://docs.python.org/2/"
- dfs = self.read_html(url, match="Python")
+ @pytest.mark.single_cpu
+ def test_multiple_matches(self, python_docs, httpserver):
+ httpserver.serve_content(content=python_docs)
+ dfs = self.read_html(httpserver.url, match="Python")
assert len(dfs) > 1
@pytest.mark.network
- @tm.network(url="https://docs.python.org/2/", check_before_test=True)
- def test_python_docs_table(self):
- url = "https://docs.python.org/2/"
- dfs = self.read_html(url, match="Python")
+ @pytest.mark.single_cpu
+ def test_python_docs_table(self, python_docs, httpserver):
+ httpserver.serve_content(content=python_docs)
+ dfs = self.read_html(httpserver.url, match="Python")
zz = [df.iloc[0, 0][0:4] for df in dfs]
- assert sorted(zz) == sorted(["Repo", "What"])
+ assert sorted(zz) == ["Pyth", "What"]
def test_empty_tables(self):
"""
diff --git a/pandas/tests/io/test_parquet.py b/pandas/tests/io/test_parquet.py
index f2ff526a58f99..35bf75d3928f8 100644
--- a/pandas/tests/io/test_parquet.py
+++ b/pandas/tests/io/test_parquet.py
@@ -376,21 +376,13 @@ def check_external_error_on_write(self, df, engine, exc):
to_parquet(df, path, engine, compression=None)
@pytest.mark.network
- @tm.network(
- url=(
- "https://raw.githubusercontent.com/pandas-dev/pandas/"
- "main/pandas/tests/io/data/parquet/simple.parquet"
- ),
- check_before_test=True,
- )
- def test_parquet_read_from_url(self, df_compat, engine):
+ @pytest.mark.single_cpu
+ def test_parquet_read_from_url(self, httpserver, datapath, df_compat, engine):
if engine != "auto":
pytest.importorskip(engine)
- url = (
- "https://raw.githubusercontent.com/pandas-dev/pandas/"
- "main/pandas/tests/io/data/parquet/simple.parquet"
- )
- df = read_parquet(url)
+ with open(datapath("io", "data", "parquet", "simple.parquet"), mode="rb") as f:
+ httpserver.serve_content(content=f.read())
+ df = read_parquet(httpserver.url)
tm.assert_frame_equal(df, df_compat)
diff --git a/pandas/tests/io/test_s3.py b/pandas/tests/io/test_s3.py
index 5171ec04b0bcf..5c23000270c99 100644
--- a/pandas/tests/io/test_s3.py
+++ b/pandas/tests/io/test_s3.py
@@ -5,7 +5,6 @@
import pandas.util._test_decorators as td
from pandas import read_csv
-import pandas._testing as tm
def test_streaming_s3_objects():
@@ -21,28 +20,24 @@ def test_streaming_s3_objects():
@td.skip_if_no("s3fs")
-@pytest.mark.network
-@tm.network
-def test_read_without_creds_from_pub_bucket():
+def test_read_without_creds_from_pub_bucket(s3_public_bucket_with_data):
# GH 34626
# Use Amazon Open Data Registry - https://registry.opendata.aws/gdelt
- result = read_csv("s3://gdelt-open-data/events/1981.csv", nrows=3)
+ result = read_csv(f"s3://{s3_public_bucket_with_data.name}/tips.csv", nrows=3)
assert len(result) == 3
@td.skip_if_no("s3fs")
-@pytest.mark.network
-@tm.network
-def test_read_with_creds_from_pub_bucket(monkeypatch):
+@pytest.mark.single_cpu
+def test_read_with_creds_from_pub_bucket(s3_public_bucket_with_data, monkeypatch):
# Ensure we can read from a public bucket with credentials
# GH 34626
- # Use Amazon Open Data Registry - https://registry.opendata.aws/gdelt
# temporary workaround as moto fails for botocore >= 1.11 otherwise,
# see https://github.com/spulec/moto/issues/1924 & 1952
monkeypatch.setenv("AWS_ACCESS_KEY_ID", "foobar_key")
monkeypatch.setenv("AWS_SECRET_ACCESS_KEY", "foobar_secret")
df = read_csv(
- "s3://gdelt-open-data/events/1981.csv", nrows=5, sep="\t", header=None
+ f"s3://{s3_public_bucket_with_data.name}/tips.csv", nrows=5, header=None
)
assert len(df) == 5
diff --git a/pandas/tests/io/xml/test_xml.py b/pandas/tests/io/xml/test_xml.py
index b0e806caecc80..80c63d0e17de1 100644
--- a/pandas/tests/io/xml/test_xml.py
+++ b/pandas/tests/io/xml/test_xml.py
@@ -14,7 +14,6 @@
import numpy as np
import pytest
-from pandas.compat import is_ci_environment
from pandas.compat._optional import import_optional_dependency
from pandas.errors import (
EmptyDataError,
@@ -297,53 +296,16 @@ def test_parser_consistency_file(xml_books):
@pytest.mark.network
-@pytest.mark.slow
-@tm.network(
- url=(
- "https://data.cityofchicago.org/api/views/"
- "8pix-ypme/rows.xml?accessType=DOWNLOAD"
- ),
- check_before_test=True,
-)
-def test_parser_consistency_url(parser):
- url = (
- "https://data.cityofchicago.org/api/views/"
- "8pix-ypme/rows.xml?accessType=DOWNLOAD"
- )
-
- with tm.ensure_clean(filename="cta.xml") as path:
- (read_xml(url, xpath=".//row/row", parser=parser).to_xml(path, index=False))
+@pytest.mark.single_cpu
+def test_parser_consistency_url(parser, httpserver):
+ httpserver.serve_content(content=xml_default_nmsp)
- df_xpath = read_xml(path, parser=parser)
- df_iter = read_xml(
- path,
- parser=parser,
- iterparse={
- "row": [
- "_id",
- "_uuid",
- "_position",
- "_address",
- "stop_id",
- "direction_id",
- "stop_name",
- "station_name",
- "station_descriptive_name",
- "map_id",
- "ada",
- "red",
- "blue",
- "g",
- "brn",
- "p",
- "pexp",
- "y",
- "pnk",
- "o",
- "location",
- ]
- },
- )
+ df_xpath = read_xml(xml_default_nmsp, parser=parser)
+ df_iter = read_xml(
+ BytesIO(xml_default_nmsp.encode()),
+ parser=parser,
+ iterparse={"row": ["shape", "degrees", "sides"]},
+ )
tm.assert_frame_equal(df_xpath, df_iter)
@@ -520,14 +482,11 @@ def test_wrong_file_path_etree():
@pytest.mark.network
-@tm.network(
- url="https://www.w3schools.com/xml/books.xml",
- check_before_test=True,
-)
@td.skip_if_no("lxml")
-def test_url():
- url = "https://www.w3schools.com/xml/books.xml"
- df_url = read_xml(url, xpath=".//book[count(*)=4]")
+def test_url(httpserver, xml_file):
+ with open(xml_file) as f:
+ httpserver.serve_content(content=f.read())
+ df_url = read_xml(httpserver.url, xpath=".//book[count(*)=4]")
df_expected = DataFrame(
{
@@ -536,7 +495,6 @@ def test_url():
"author": ["Giada De Laurentiis", "J K. Rowling", "Erik T. Ray"],
"year": [2005, 2005, 2003],
"price": [30.00, 29.99, 39.95],
- "cover": [None, None, "paperback"],
}
)
@@ -544,11 +502,11 @@ def test_url():
@pytest.mark.network
-@tm.network(url="https://www.w3schools.com/xml/python.xml", check_before_test=True)
-def test_wrong_url(parser):
- with pytest.raises(HTTPError, match=("HTTP Error 404: Not Found")):
- url = "https://www.w3schools.com/xml/python.xml"
- read_xml(url, xpath=".//book[count(*)=4]", parser=parser)
+@pytest.mark.single_cpu
+def test_wrong_url(parser, httpserver):
+ httpserver.serve_content("NOT FOUND", code=404)
+ with pytest.raises(HTTPError, match=("HTTP Error 404: NOT FOUND")):
+ read_xml(httpserver.url, xpath=".//book[count(*)=4]", parser=parser)
# XPATH
@@ -1429,17 +1387,18 @@ def test_file_io_iterparse(xml_books, parser, mode):
@pytest.mark.network
-@tm.network(url="https://www.w3schools.com/xml/books.xml", check_before_test=True)
-def test_url_path_error(parser):
- url = "https://www.w3schools.com/xml/books.xml"
- with pytest.raises(
- ParserError, match=("iterparse is designed for large XML files")
- ):
- read_xml(
- url,
- parser=parser,
- iterparse={"row": ["shape", "degrees", "sides", "date"]},
- )
+@pytest.mark.single_cpu
+def test_url_path_error(parser, httpserver, xml_file):
+ with open(xml_file) as f:
+ httpserver.serve_content(content=f.read())
+ with pytest.raises(
+ ParserError, match=("iterparse is designed for large XML files")
+ ):
+ read_xml(
+ httpserver.url,
+ parser=parser,
+ iterparse={"row": ["shape", "degrees", "sides", "date"]},
+ )
def test_compression_error(parser, compression_only):
@@ -1641,14 +1600,245 @@ def test_empty_data(xml_books, parser):
)
-@pytest.mark.network
@td.skip_if_no("lxml")
-@tm.network(
- url="https://www.w3schools.com/xml/cdcatalog_with_xsl.xml", check_before_test=True
-)
def test_online_stylesheet():
- xml = "https://www.w3schools.com/xml/cdcatalog_with_xsl.xml"
- xsl = "https://www.w3schools.com/xml/cdcatalog.xsl"
+ xml = """\
+
+