scrape-cli 1.3.0__tar.gz → 1.3.2__tar.gz

{scrape_cli-1.3.0 → scrape_cli-1.3.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: scrape_cli
-Version: 1.3.0
+Version: 1.3.2
 Summary: It's a command-line tool to extract HTML elements using an XPath query or CSS3 selector.
 Author-email: Andrea Borruso <aborruso@gmail.com>
 Project-URL: Homepage, https://github.com/aborruso/scrape-cli
@@ -72,6 +72,7 @@ pip install -e .
 - requests
 - lxml
 - cssselect
+- xmltodict
 
 ## How does it work?
 
@@ -280,10 +281,12 @@ Output:
 }
 ```
 
-`-j` automatically wraps the result in `<html>/<body>` before conversion, so you don't need to pass `-b`. The output is the same you would get from `scrape -be ... | xq .` (the underlying converter is `xmltodict`, the same library used by `xq`).
+`-j` automatically wraps the result in `<html>/<body>` before conversion, so you don't need to pass `-b`. For elements, the output is the same you would get from `scrape -be ... | xq .` (the underlying converter is `xmltodict`, the same library used by `xq`). Expressions that return only strings, such as `//a/@href` or `//p/text()`, give the string in `body` when there is one result and an array when there are more.
 
 `-j` is mutually exclusive with `-t`, `-x` (`--check-existence`) and `-a` (`--argument`).
 
+`-j` exits with an error when a matched element has an attribute name that is not valid XML, such as `@click` or `:bind`.
+
 Useful for JSON-based pipelines, APIs, databases, and processing with jq/DuckDB.
 
 Some notes on the commands:

{scrape_cli-1.3.0 → scrape_cli-1.3.2}/README.md

@@ -57,6 +57,7 @@ pip install -e .
 - requests
 - lxml
 - cssselect
+- xmltodict
 
 ## How does it work?
 
@@ -265,10 +266,12 @@ Output:
 }
 ```
 
-`-j` automatically wraps the result in `<html>/<body>` before conversion, so you don't need to pass `-b`. The output is the same you would get from `scrape -be ... | xq .` (the underlying converter is `xmltodict`, the same library used by `xq`).
+`-j` automatically wraps the result in `<html>/<body>` before conversion, so you don't need to pass `-b`. For elements, the output is the same you would get from `scrape -be ... | xq .` (the underlying converter is `xmltodict`, the same library used by `xq`). Expressions that return only strings, such as `//a/@href` or `//p/text()`, give the string in `body` when there is one result and an array when there are more.
 
 `-j` is mutually exclusive with `-t`, `-x` (`--check-existence`) and `-a` (`--argument`).
 
+`-j` exits with an error when a matched element has an attribute name that is not valid XML, such as `@click` or `:bind`.
+
 Useful for JSON-based pipelines, APIs, databases, and processing with jq/DuckDB.
 
 Some notes on the commands:

{scrape_cli-1.3.0 → scrape_cli-1.3.2}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "scrape_cli"
-version = "1.3.0"
+version = "1.3.2"
 description = "It's a command-line tool to extract HTML elements using an XPath query or CSS3 selector."
 readme = "README.md"
 authors = [

{scrape_cli-1.3.0 → scrape_cli-1.3.2}/scrape_cli/__init__.py

@@ -4,7 +4,7 @@ scrape-cli - A command-line tool to extract HTML elements using XPath or CSS3 se
 
 from scrape_cli.scrape import main
 
-__version__ = "1.3.0"
+__version__ = "1.3.2"
 __author__ = "Andrea Borruso"
 __author_email__ = "aborruso@gmail.com"
 

{scrape_cli-1.3.0 → scrape_cli-1.3.2}/scrape_cli/scrape.py

@@ -6,7 +6,7 @@
 # $ curl 'https://en.wikipedia.org/wiki/List_of_sovereign_states' -s \
 # | scrape -e 'table.wikitable > tbody > tr > td > b > a'
 #
-# Dependencies: lxml, cssselect, requests
+# Dependencies: lxml, cssselect, requests, xmltodict
 #
 # Author: http://jeroenjanssens.com
 
@@ -19,6 +19,8 @@ import requests
 import xmltodict
 from lxml import etree
 from cssselect import GenericTranslator
+from xml.parsers.expat import ExpatError
+from xml.sax.saxutils import escape
 
 # Read version from __init__.py
 init_file = os.path.join(os.path.dirname(__file__), '__init__.py')
@@ -54,6 +56,21 @@ def convert_css_to_xpath(expression):
         print(f"Error converting CSS selector to XPath: {e}", file=sys.stderr)
         sys.exit(1)
 
+def xpath_result_items(result):
+    """XPath functions return a single string, number or boolean instead of a node list."""
+    if isinstance(result, list):
+        return result
+    if isinstance(result, bool):
+        return ['true' if result else 'false']
+    if isinstance(result, float):
+        return [str(int(result)) if result.is_integer() else str(result)]
+    return [result] if result else []
+
+
+def wrap_in_body(results):
+    return "<!DOCTYPE html>\n<html>\n<body>\n" + "".join(r + "\n" for r in results) + "</body>\n</html>\n"
+
+
 def is_xpath(expression):
     """
     Check if the expression is XPath by looking for common XPath patterns:
@@ -118,13 +135,10 @@ examples:
     parser.add_argument('--version', action='version', version=f'%(prog)s {__version__}')
 
     # Check for incorrect argument order (-eb instead of -be, -ej instead of -je)
-    joined_argv = ' '.join(sys.argv)
-    if '-eb' in joined_argv:
-        print("Error: use -be not -eb.\n  scrape -be \"//article\" file.html", file=sys.stderr)
-        sys.exit(1)
-    if '-ej' in joined_argv:
-        print("Error: use -je not -ej.\n  scrape -je \"//article\" file.html", file=sys.stderr)
-        sys.exit(1)
+    for wrong, right in (('-eb', '-be'), ('-ej', '-je')):
+        if wrong in sys.argv[1:]:
+            print(f"Error: use {right} not {wrong}.\n  scrape {right} \"//article\" file.html", file=sys.stderr)
+            sys.exit(1)
     # Defines the HTML input argument (can be a file, URL or stdin)
     parser.add_argument('html', nargs='?', type=str, default='',
                         help="HTML input (file, URL or stdin, default: stdin)", metavar="HTML")
@@ -262,13 +276,16 @@ examples:
         sys.exit(1)
 
     results = []
+    string_results = []
     # For each expression, perform the search in the parsed HTML
     for e in expression:
-        els = list(document.xpath(e))
+        result = document.xpath(e)
 
         # If check-existence is enabled, return 0 or 1 depending on the existence of elements
         if args.check_existence:
-            sys.exit(1 if len(els) == 0 else 0)
+            sys.exit(0 if result else 1)
+
+        els = xpath_result_items(result)
 
         # Extract the text or content of the found elements
         for el in els:
@@ -278,6 +295,10 @@ examples:
                 # Clean the text when using -t option
                 if args.text:
                     text = clean_text(text)
+                # Strings are plain text, but -j parses the results as XML
+                if args.json:
+                    string_results.append(text.strip())
+                    text = escape(text)
             elif args.text:
                 # If -t option is used, extract only text content
                 if hasattr(el, 'text_content'):
@@ -303,14 +324,20 @@ examples:
 
     # Output handling
     if args.json:
-        wrapped = "<!DOCTYPE html>\n<html>\n<body>\n" + "".join(r + "\n" for r in results) + "</body>\n</html>\n"
-        parsed = xmltodict.parse(wrapped)
+        values = [s for s in string_results if s]
+        if values and len(string_results) == len(results):
+            # Only strings (@attr, text()): XML conversion would merge them into one
+            parsed = {"html": {"body": values[0] if len(values) == 1 else values}}
+        else:
+            try:
+                parsed = xmltodict.parse(wrap_in_body(results))
+            except ExpatError as e:
+                print(f"Error: cannot convert result to JSON, it is not valid XML ({e}). "
+                      "Attribute names like @click or :bind are not supported by -j.", file=sys.stderr)
+                sys.exit(1)
         sys.stdout.write(json.dumps(parsed, indent=2, ensure_ascii=False) + "\n")
     elif args.body and not args.text:
-        sys.stdout.write("<!DOCTYPE html>\n<html>\n<body>\n")
-        for result in results:
-            sys.stdout.write(result + "\n")
-        sys.stdout.write("</body>\n</html>\n")
+        sys.stdout.write(wrap_in_body(results))
     else:
         # Normal output (or text-only output when -t is used)
         for result in results:

{scrape_cli-1.3.0 → scrape_cli-1.3.2}/scrape_cli.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: scrape_cli
-Version: 1.3.0
+Version: 1.3.2
 Summary: It's a command-line tool to extract HTML elements using an XPath query or CSS3 selector.
 Author-email: Andrea Borruso <aborruso@gmail.com>
 Project-URL: Homepage, https://github.com/aborruso/scrape-cli
@@ -72,6 +72,7 @@ pip install -e .
 - requests
 - lxml
 - cssselect
+- xmltodict
 
 ## How does it work?
 
@@ -280,10 +281,12 @@ Output:
 }
 ```
 
-`-j` automatically wraps the result in `<html>/<body>` before conversion, so you don't need to pass `-b`. The output is the same you would get from `scrape -be ... | xq .` (the underlying converter is `xmltodict`, the same library used by `xq`).
+`-j` automatically wraps the result in `<html>/<body>` before conversion, so you don't need to pass `-b`. For elements, the output is the same you would get from `scrape -be ... | xq .` (the underlying converter is `xmltodict`, the same library used by `xq`). Expressions that return only strings, such as `//a/@href` or `//p/text()`, give the string in `body` when there is one result and an array when there are more.
 
 `-j` is mutually exclusive with `-t`, `-x` (`--check-existence`) and `-a` (`--argument`).
 
+`-j` exits with an error when a matched element has an attribute name that is not valid XML, such as `@click` or `:bind`.
+
 Useful for JSON-based pipelines, APIs, databases, and processing with jq/DuckDB.
 
 Some notes on the commands:

{scrape_cli-1.3.0 → scrape_cli-1.3.2}/tests/test_scrape.py

@@ -183,6 +183,26 @@ def test_incorrect_eb_order_exits_with_specific_message():
     assert "use -be not -eb" in result.stderr
 
 
+def test_incorrect_ej_order_exits_with_specific_message():
+    result = run_scrape("-ej")
+
+    assert result.returncode == 1
+    assert "use -je not -ej" in result.stderr
+
+
+def test_order_checks_ignore_filenames_and_selectors(tmp_path):
+    for name in ("page-eb.html", "page-ej.html"):
+        html_file = tmp_path / name
+        html_file.write_text("<h1>ok</h1>", encoding="utf-8")
+        result = run_scrape(str(html_file), "-e", "h1")
+        assert result.returncode == 0, result.stderr
+        assert "ok" in result.stdout
+
+    for selector in (".page-ejected", ".page-ebook"):
+        result = run_scrape("-e", selector, input_data='<p class="x">ok</p>')
+        assert "use -" not in result.stderr
+
+
 def test_invalid_css_selector_fails_conversion():
     result = run_scrape(str(TEST_HTML), "-e", "div[")
 
@@ -235,6 +255,92 @@ def test_json_flag_conflicts_with_text_check_existence_argument():
     assert "cannot be combined" in ja.stderr
 
 
+def test_json_flag_handles_string_results_with_special_characters():
+    html = '<a href="x?a=1&amp;b=2">AT&amp;T &lt;b&gt;</a>'
+
+    attr = run_scrape("-je", "//a/@href", input_data=html)
+    assert attr.returncode == 0, attr.stderr
+    assert json.loads(attr.stdout)["html"]["body"] == "x?a=1&b=2"
+
+    text = run_scrape("-je", "//a/text()", input_data=html)
+    assert text.returncode == 0, text.stderr
+    assert json.loads(text.stdout)["html"]["body"] == "AT&T <b>"
+
+
+def test_json_flag_returns_array_for_multiple_string_results():
+    html = '<a href="x?a=1&amp;b=2">uno</a> <a href="y">due</a>'
+
+    attrs = run_scrape("-je", "//a/@href", input_data=html)
+    assert attrs.returncode == 0, attrs.stderr
+    assert json.loads(attrs.stdout)["html"]["body"] == ["x?a=1&b=2", "y"]
+
+    # Whitespace-only text nodes are not results
+    texts = run_scrape("-je", "//body//text()", input_data=html)
+    assert json.loads(texts.stdout)["html"]["body"] == ["uno", "due"]
+
+
+def test_json_flag_mixed_elements_and_strings_still_converts():
+    result = run_scrape("-je", "//a | //a/@href", input_data='<a href="x&amp;y">uno</a>')
+
+    assert result.returncode == 0, result.stderr
+    body = json.loads(result.stdout)["html"]["body"]
+    assert body["a"]["#text"] == "uno"
+    assert body["#text"] == "x&y"
+
+
+SCALAR_HTML = "<h1>Ciao</h1><a>1</a><a>2</a>"
+
+
+def test_xpath_functions_return_a_single_value():
+    cases = {
+        "string(//h1)": "Ciao\n",
+        "count(//a)": "2\n",
+        "boolean(//a)": "true\n",
+        "boolean(//nulla)": "false\n",
+        "string(//nulla)": "",
+    }
+    for expression, expected in cases.items():
+        result = run_scrape("-e", expression, input_data=SCALAR_HTML)
+        assert result.returncode == 0, result.stderr
+        assert result.stdout == expected, expression
+
+
+def test_check_existence_follows_xpath_function_value():
+    for expression, expected in {
+        "string(//h1)": 0,
+        "string(//nulla)": 1,
+        "count(//a)": 0,
+        "count(//nulla)": 1,
+        "boolean(//a)": 0,
+        "boolean(//nulla)": 1,
+    }.items():
+        result = run_scrape("-x", "-e", expression, input_data=SCALAR_HTML)
+        assert result.returncode == expected, expression
+
+
+def test_json_flag_with_xpath_functions():
+    for expression, expected in {"string(//h1)": "Ciao", "count(//a)": "2"}.items():
+        result = run_scrape("-je", expression, input_data=SCALAR_HTML)
+        assert result.returncode == 0, result.stderr
+        assert json.loads(result.stdout)["html"]["body"] == expected
+
+
+def test_json_flag_text_results_work_on_test_file():
+    result = run_scrape(str(TEST_HTML), "-je", "//p/text()")
+
+    assert result.returncode == 0, result.stderr
+    assert json.loads(result.stdout)["html"]["body"]
+
+
+def test_json_flag_reports_clean_error_on_non_xml_attribute_name():
+    result = run_scrape("-je", "#v", input_data='<div id="v" @click="go">x</div>')
+
+    assert result.returncode == 1
+    assert "Error:" in result.stderr
+    assert "Traceback" not in result.stderr
+    assert result.stdout == ""
+
+
 def test_url_input_downloads_and_extracts_text():
     html_bytes = TEST_HTML.read_bytes()
     server, thread = run_test_server(html_bytes)