Add line numbers and removed unneeded dependency

inlinehashes/__init__.py

@@ -1,4 +1,4 @@
 from .lib import parse
 
-__version__ = "0.0.3"
+__version__ = "0.0.4"
 __all__ = ["parse"]

inlinehashes/app.py

@@ -5,7 +5,8 @@ this library. It makes use of the same tools available for those that
 install the package in order to be used programatically.
 """
 from typing import List
-import requests
+from urllib.request import urlopen, Request
+from urllib.error import URLError
 import argparse
 import inlinehashes
 import json
@@ -16,20 +17,18 @@ def build_output(
 ) -> str:
     """Build a JSON output from a list of Inline objects."""
     snippet = "content" if full else "short_content"
-    out = [{"content": getattr(i, snippet), "hash": getattr(i, alg)} for i in inlines]
+    out = [
+        {
+            "content": getattr(i, snippet),
+            "hash": getattr(i, alg),
+            "line": i.line,
+            "position": i.position,
+        }
+        for i in inlines
+    ]
     return json.dumps(out, indent=2)
 
 
-def write_to_file(path: str, content: str) -> None:
-    """Writes the content to the specified file.
-
-    raises:
-        OSError: More than one subclass of OSError
-    """
-    with open(path, "w") as f:
-        f.write(content)
-
-
 def run_cli() -> None:
     """Entry point of the command line interface."""
     parser = argparse.ArgumentParser()
@@ -47,29 +46,36 @@ def run_cli() -> None:
         help="Include full content in the output",
         action="store_true",
     )
-    parser.add_argument("-o", "--output", help="Store output in a file.")
+    parser.add_argument(
+        "-t",
+        "--target",
+        help="Target inline content to look for",
+        default="all",
+        choices=["all", "scripts", "styles"],
+    )
     args = parser.parse_args()
     path = args.source
+    target = args.target
 
     try:
         if path.startswith("http://") or path.startswith("https://"):
-            response = requests.get(path)
-            response.raise_for_status()
-            content = response.text
+            req = Request(
+                path,
+                headers={"User-Agent": f"Inlinehashes[{inlinehashes.__version__}]"},
+            )
+            with urlopen(req) as response:
+                content = response.read()
         else:
             with open(path, "r") as f:
                 content = f.read()
-    except (requests.RequestException, OSError):
-        print(f"Invalid source: {path}")
+    except (URLError, OSError) as error:
+        print(error)
+        print(f"Failed to get source: {path}")
         exit(1)
 
-    inlines = inlinehashes.parse(content)
+    inlines = inlinehashes.parse(content, target)
     out = build_output(inlines, args.alg, bool(args.full))
-
-    if args.output:
-        write_to_file(args.output, out)
-    else:
-        print(out)
+    print(out)
 
 
 if __name__ == "__main__":

inlinehashes/lib.py

@@ -29,6 +29,8 @@ class Inline:
     """
 
     content: str
+    line: Optional[int] = None
+    position: Optional[int] = None
 
     @cached_property
     def short_content(self) -> str:
@@ -53,7 +55,7 @@ class Inline:
         return f"sha512-{h_b64}"
 
     def __repr__(self) -> str:
-        return f"Inline(content='{self.content}')"
+        return f"Inline(content='{self.content}', line='{self.line}', postiion='{self.position}')"
 
     def __str__(self) -> str:
         return f"Inline(content='{self.short_content}...')"
@@ -205,10 +207,10 @@ def parse(content: str, target: str = "all") -> List[Inline]:
     for q in search_queries:
         for tag in soup.find_all(q.search_function):
             if q.attr_name:
-                inline = Inline(tag[q.attr_name])
+                inline = Inline(tag[q.attr_name], tag.sourceline, tag.sourcepos)
             else:
                 if not tag.contents:
                     continue
-                inline = Inline(tag.contents[0])
+                inline = Inline(tag.contents[0], tag.sourceline, tag.sourcepos)
             elements.append(inline)
     return elements

poetry.lock

@@ -57,25 +57,6 @@ d = ["aiohttp (>=3.7.4)"]
 jupyter = ["ipython (>=7.8.0)", "tokenize-rt (>=3.2.0)"]
 uvloop = ["uvloop (>=0.15.2)"]
 
-[[package]]
-name = "certifi"
-version = "2021.10.8"
-description = "Python package for providing Mozilla's CA Bundle."
-category = "main"
-optional = false
-python-versions = "*"
-
-[[package]]
-name = "charset-normalizer"
-version = "2.0.12"
-description = "The Real First Universal Charset Detector. Open, modern and actively maintained alternative to Chardet."
-category = "main"
-optional = false
-python-versions = ">=3.5.0"
-
-[package.extras]
-unicode_backport = ["unicodedata2"]
-
 [[package]]
 name = "click"
 version = "8.0.4"
@@ -95,14 +76,6 @@ category = "dev"
 optional = false
 python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*, !=3.4.*"
 
-[[package]]
-name = "idna"
-version = "3.3"
-description = "Internationalized Domain Names in Applications (IDNA)"
-category = "main"
-optional = false
-python-versions = ">=3.5"
-
 [[package]]
 name = "more-itertools"
 version = "8.12.0"
@@ -220,24 +193,6 @@ wcwidth = "*"
 checkqa-mypy = ["mypy (==v0.761)"]
 testing = ["argcomplete", "hypothesis (>=3.56)", "mock", "nose", "requests", "xmlschema"]
 
-[[package]]
-name = "requests"
-version = "2.27.1"
-description = "Python HTTP for Humans."
-category = "main"
-optional = false
-python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*, !=3.4.*, !=3.5.*"
-
-[package.dependencies]
-certifi = ">=2017.4.17"
-charset-normalizer = {version = ">=2.0.0,<2.1.0", markers = "python_version >= \"3\""}
-idna = {version = ">=2.5,<4", markers = "python_version >= \"3\""}
-urllib3 = ">=1.21.1,<1.27"
-
-[package.extras]
-socks = ["PySocks (>=1.5.6,!=1.5.7)", "win-inet-pton"]
-use_chardet_on_py3 = ["chardet (>=3.0.2,<5)"]
-
 [[package]]
 name = "soupsieve"
 version = "2.3.1"
@@ -262,19 +217,6 @@ category = "dev"
 optional = false
 python-versions = ">=3.6"
 
-[[package]]
-name = "urllib3"
-version = "1.26.8"
-description = "HTTP library with thread-safe connection pooling, file post, and more."
-category = "main"
-optional = false
-python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*, !=3.4.*, <4"
-
-[package.extras]
-brotli = ["brotlipy (>=0.6.0)"]
-secure = ["pyOpenSSL (>=0.14)", "cryptography (>=1.3.4)", "idna (>=2.0.0)", "certifi", "ipaddress"]
-socks = ["PySocks (>=1.5.6,!=1.5.7,<2.0)"]
-
 [[package]]
 name = "wcwidth"
 version = "0.2.5"
@@ -286,7 +228,7 @@ python-versions = "*"
 [metadata]
 lock-version = "1.1"
 python-versions = "^3.9"
-content-hash = "5d3261ad45347af8277dd3042f42feb5beff0861143dee17cc632c823534a859"
+content-hash = "4da6f6565f351fd70096e9f8bb34b6958cc7e223fb9d87f59eba607c7ec96264"
 
 [metadata.files]
 atomicwrites = [
@@ -326,14 +268,6 @@ black = [
     {file = "black-22.1.0-py3-none-any.whl", hash = "sha256:3524739d76b6b3ed1132422bf9d82123cd1705086723bc3e235ca39fd21c667d"},
     {file = "black-22.1.0.tar.gz", hash = "sha256:a7c0192d35635f6fc1174be575cb7915e92e5dd629ee79fdaf0dcfa41a80afb5"},
 ]
-certifi = [
-    {file = "certifi-2021.10.8-py2.py3-none-any.whl", hash = "sha256:d62a0163eb4c2344ac042ab2bdf75399a71a2d8c7d47eac2e2ee91b9d6339569"},
-    {file = "certifi-2021.10.8.tar.gz", hash = "sha256:78884e7c1d4b00ce3cea67b44566851c4343c120abd683433ce934a68ea58872"},
-]
-charset-normalizer = [
-    {file = "charset-normalizer-2.0.12.tar.gz", hash = "sha256:2857e29ff0d34db842cd7ca3230549d1a697f96ee6d3fb071cfa6c7393832597"},
-    {file = "charset_normalizer-2.0.12-py3-none-any.whl", hash = "sha256:6881edbebdb17b39b4eaaa821b438bf6eddffb4468cf344f09f89def34a8b1df"},
-]
 click = [
     {file = "click-8.0.4-py3-none-any.whl", hash = "sha256:6a7a62563bbfabfda3a38f3023a1db4a35978c0abd76f6c9605ecd6554d6d9b1"},
     {file = "click-8.0.4.tar.gz", hash = "sha256:8458d7b1287c5fb128c90e23381cf99dcde74beaf6c7ff6384ce84d6fe090adb"},
@@ -342,10 +276,6 @@ colorama = [
     {file = "colorama-0.4.4-py2.py3-none-any.whl", hash = "sha256:9f47eda37229f68eee03b24b9748937c7dc3868f906e8ba69fbcbdd3bc5dc3e2"},
     {file = "colorama-0.4.4.tar.gz", hash = "sha256:5941b2b48a20143d2267e95b1c2a7603ce057ee39fd88e7329b0c292aa16869b"},
 ]
-idna = [
-    {file = "idna-3.3-py3-none-any.whl", hash = "sha256:84d9dd047ffa80596e0f246e2eab0b391788b0503584e8945f2368256d2735ff"},
-    {file = "idna-3.3.tar.gz", hash = "sha256:9d643ff0a55b762d5cdb124b8eaa99c66322e2157b69160bc32796e824360e6d"},
-]
 more-itertools = [
     {file = "more-itertools-8.12.0.tar.gz", hash = "sha256:7dc6ad46f05f545f900dd59e8dfb4e84a4827b97b3cfecb175ea0c7d247f6064"},
     {file = "more_itertools-8.12.0-py3-none-any.whl", hash = "sha256:43e6dd9942dffd72661a2c4ef383ad7da1e6a3e968a927ad7a6083ab410a688b"},
@@ -407,10 +337,6 @@ pytest = [
     {file = "pytest-5.4.3-py3-none-any.whl", hash = "sha256:5c0db86b698e8f170ba4582a492248919255fcd4c79b1ee64ace34301fb589a1"},
     {file = "pytest-5.4.3.tar.gz", hash = "sha256:7979331bfcba207414f5e1263b5a0f8f521d0f457318836a7355531ed1a4c7d8"},
 ]
-requests = [
-    {file = "requests-2.27.1-py2.py3-none-any.whl", hash = "sha256:f22fa1e554c9ddfd16e6e41ac79759e17be9e492b3587efa038054674760e72d"},
-    {file = "requests-2.27.1.tar.gz", hash = "sha256:68d7c56fd5a8999887728ef304a6d12edc7be74f1cfa47714fc8b414525c9a61"},
-]
 soupsieve = [
     {file = "soupsieve-2.3.1-py3-none-any.whl", hash = "sha256:1a3cca2617c6b38c0343ed661b1fa5de5637f257d4fe22bd9f1338010a1efefb"},
     {file = "soupsieve-2.3.1.tar.gz", hash = "sha256:b8d49b1cd4f037c7082a9683dfa1801aa2597fb11c3a1155b7a5b94829b4f1f9"},
@@ -423,10 +349,6 @@ typing-extensions = [
     {file = "typing_extensions-4.1.1-py3-none-any.whl", hash = "sha256:21c85e0fe4b9a155d0799430b0ad741cdce7e359660ccbd8b530613e8df88ce2"},
     {file = "typing_extensions-4.1.1.tar.gz", hash = "sha256:1a9462dcc3347a79b1f1c0271fbe79e844580bb598bafa1ed208b94da3cdcd42"},
 ]
-urllib3 = [
-    {file = "urllib3-1.26.8-py2.py3-none-any.whl", hash = "sha256:000ca7f471a233c2251c6c7023ee85305721bfdf18621ebff4fd17a8653427ed"},
-    {file = "urllib3-1.26.8.tar.gz", hash = "sha256:0e7c33d9a63e7ddfcb86780aac87befc2fbddf46c58dbb487e0855f7ceec283c"},
-]
 wcwidth = [
     {file = "wcwidth-0.2.5-py2.py3-none-any.whl", hash = "sha256:beb4802a9cebb9144e99086eff703a642a13d6a0052920003a230f3294bbe784"},
     {file = "wcwidth-0.2.5.tar.gz", hash = "sha256:c4d647b99872929fdb7bdcaa4fbe7f01413ed3d98077df798530e5b04f116c83"},

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "inlinehashes"
-version = "0.0.3"
+version = "0.0.4"
 description = "Hash generator for HTML inline styles and scripts"
 authors = ["Gonçalo Valério <gon@ovalerio.net>"]
 homepage = "https://github.com/dethos/inlinehashes"
@@ -22,7 +22,6 @@ classifiers = [
 [tool.poetry.dependencies]
 python = "^3.9"
 beautifulsoup4 = "^4.10.0"
-requests = "^2.27.1"
 
 [tool.poetry.dev-dependencies]
 pytest = "^5.2"

tests/test_inlinehashes.py

@@ -117,6 +117,8 @@ class TestParse:
         inlines = parse(doc)
         assert len(inlines) == 1
         assert inlines[0].content == 'alert("hash this");'
+        assert inlines[0].line == 5
+        assert inlines[0].position == 8
 
     def test_parse_detects_style_tags(self):
         doc = """
@@ -131,6 +133,8 @@ class TestParse:
         inlines = parse(doc)
         assert len(inlines) == 1
         assert inlines[0].content == ".someclass { background:#142a3f; }"
+        assert inlines[0].line == 5
+        assert inlines[0].position == 10
 
     def test_parse_detects_style_attributes(self):
         doc = """
@@ -144,6 +148,8 @@ class TestParse:
         inlines = parse(doc)
         assert len(inlines) == 1
         assert inlines[0].content == "text-color: #000;"
+        assert inlines[0].line == 6
+        assert inlines[0].position == 8
 
     @pytest.mark.parametrize("attr", _EVENT_HANDLER_ATTRS)
     def test_parse_detect_attributes_with_js(self, attr):
@@ -160,7 +166,54 @@ class TestParse:
         inlines = parse(doc)
         assert len(inlines) == 1
         assert inlines[0].content == "alert(1);"
+        assert inlines[0].line == 6
+        assert inlines[0].position == 8
+
+    def test_parse_both_targets(self):
+        doc = """
+        <html>
+        <head>
+          <title>Some title</title>
+          <style>.someclass { background:#142a3f; }</style>
+        </head>
+        <body onclick="alert(1);">Some body</body>
+        </html>
+        """
+        inlines = parse(doc)
+        assert len(inlines) == 2
+
+    def test_parse_only_script_targets(self):
+        doc = """
+        <html>
+        <head>
+          <title>Some title</title>
+          <style>.someclass { background:#142a3f; }</style>
+        </head>
+        <body onclick="alert(1);">Some body</body>
+        </html>
+        """
+        inlines = parse(doc, "scripts")
+        assert len(inlines) == 1
+        assert inlines[0].content == "alert(1);"
+        assert inlines[0].line == 7
+        assert inlines[0].position == 8
+
+    def test_parse_only_style_targets(self):
+        doc = """
+        <html>
+        <head>
+          <title>Some title</title>
+          <style>.someclass { background:#142a3f; }</style>
+        </head>
+        <body onclick="alert(1);">Some body</body>
+        </html>
+        """
+        inlines = parse(doc, "styles")
+        assert len(inlines) == 1
+        assert inlines[0].content == ".someclass { background:#142a3f; }"
+        assert inlines[0].line == 5
+        assert inlines[0].position == 10
 
 
 def test_version():
-    assert __version__ == "0.0.3"
+    assert __version__ == "0.0.4"