googlenewsdecoder 0.1.0__py3-none-any.whl

googlenewsdecoder/__init__.py

@@ -0,0 +1,2 @@
+from .decoderv1 import decode_google_news_url as decoderv1
+from .decoderv2 import decode_google_news_url as decoderv2

googlenewsdecoder/decoderv1.py

@@ -0,0 +1,40 @@
+import base64
+from urllib.parse import urlparse
+
+
+def decode_google_news_url(source_url):
+    url = urlparse(source_url)
+    path = url.path.split("/")
+    if (
+        url.hostname == "news.google.com"
+        and len(path) > 1
+        and path[len(path) - 2] == "articles"
+    ):
+        base64_str = path[len(path) - 1]
+        decoded_bytes = base64.urlsafe_b64decode(base64_str + "==")
+        decoded_str = decoded_bytes.decode("latin1")
+
+        prefix = bytes([0x08, 0x13, 0x22]).decode("latin1")
+        if decoded_str.startswith(prefix):
+            decoded_str = decoded_str[len(prefix) :]
+
+        suffix = bytes([0xD2, 0x01, 0x00]).decode("latin1")
+        if decoded_str.endswith(suffix):
+            decoded_str = decoded_str[: -len(suffix)]
+
+        bytes_array = bytearray(decoded_str, "latin1")
+        length = bytes_array[0]
+        if length >= 0x80:
+            decoded_str = decoded_str[2 : length + 1]
+        else:
+            decoded_str = decoded_str[1 : length + 1]
+
+        return decoded_str
+    else:
+        return source_url
+
+
+# # Example usage:
+# if __name__ == "__main__":
+#     source_url = "https://news.google.com/rss/articles/CBMiLmh0dHBzOi8vd3d3LmJiYy5jb20vbmV3cy9hcnRpY2xlcy9jampqbnhkdjE4OG_SATJodHRwczovL3d3dy5iYmMuY29tL25ld3MvYXJ0aWNsZXMvY2pqam54ZHYxODhvLmFtcA?oc=5"
+#     print(decode_google_news_url(source_url))

googlenewsdecoder/decoderv2.py

@@ -0,0 +1,77 @@
+import requests
+import base64
+
+
+def fetch_decoded_batch_execute(id):
+    s = (
+        '[[["Fbv4je","[\\"garturlreq\\",[[\\"en-US\\",\\"US\\",[\\"FINANCE_TOP_INDICES\\",\\"WEB_TEST_1_0_0\\"],'
+        'null,null,1,1,\\"US:en\\",null,180,null,null,null,null,null,0,null,null,[1608992183,723341000]],'
+        '\\"en-US\\",\\"US\\",1,[2,3,4,8],1,0,\\"655000234\\",0,0,null,0],\\"'
+        + id
+        + '\\"]",null,"generic"]]]'
+    )
+
+    headers = {
+        "Content-Type": "application/x-www-form-urlencoded;charset=utf-8",
+        "Referer": "https://news.google.com/",
+    }
+
+    response = requests.post(
+        "https://news.google.com/_/DotsSplashUi/data/batchexecute?rpcids=Fbv4je",
+        headers=headers,
+        data={"f.req": s},
+    )
+
+    if response.status_code != 200:
+        raise Exception("Failed to fetch data from Google.")
+
+    text = response.text
+    header = '[\\"garturlres\\",\\"'
+    footer = '\\",'
+    if header not in text:
+        raise Exception(f"Header not found in response: {text}")
+    start = text.split(header, 1)[1]
+    if footer not in start:
+        raise Exception("Footer not found in response.")
+    url = start.split(footer, 1)[0]
+    return url
+
+
+def decode_google_news_url(source_url):
+    url = requests.utils.urlparse(source_url)
+    path = url.path.split("/")
+    if url.hostname == "news.google.com" and len(path) > 1 and path[-2] == "articles":
+        base64_str = path[-1]
+        decoded_bytes = base64.urlsafe_b64decode(base64_str + "==")
+        decoded_str = decoded_bytes.decode("latin1")
+
+        prefix = b"\x08\x13\x22".decode("latin1")
+        if decoded_str.startswith(prefix):
+            decoded_str = decoded_str[len(prefix) :]
+
+        suffix = b"\xd2\x01\x00".decode("latin1")
+        if decoded_str.endswith(suffix):
+            decoded_str = decoded_str[: -len(suffix)]
+
+        bytes_array = bytearray(decoded_str, "latin1")
+        length = bytes_array[0]
+        if length >= 0x80:
+            decoded_str = decoded_str[2 : length + 1]
+        else:
+            decoded_str = decoded_str[1 : length + 1]
+
+        if decoded_str.startswith("AU_yqL"):
+            return fetch_decoded_batch_execute(base64_str)
+
+        return decoded_str
+    else:
+        return source_url
+
+
+# # Example usage
+# if __name__ == "__main__":
+#     # source_url = "https://news.google.com/rss/articles/CBMiLmh0dHBzOi8vd3d3LmJiYy5jb20vbmV3cy9hcnRpY2xlcy9jampqbnhkdjE4OG_SATJodHRwczovL3d3dy5iYmMuY29tL25ld3MvYXJ0aWNsZXMvY2pqam54ZHYxODhvLmFtcA?oc=5"
+#     # source_url = "https://news.google.com/rss/articles/CBMiVkFVX3lxTE4zaGU2bTY2ZGkzdTRkSkJ0cFpsTGlDUjkxU2FBRURaTWU0c3QzVWZ1MHZZNkZ5Vzk1ZVBnTDFHY2R6ZmdCUkpUTUJsS1pqQTlCRzlzbHV3?oc=5"
+#     source_url = "https://news.google.com/rss/articles/CBMiqwFBVV95cUxNMTRqdUZpNl9hQldXbGo2YVVLOGFQdkFLYldlMUxUVlNEaElsYjRRODVUMkF3R1RYdWxvT1NoVzdUYS0xSHg3eVdpTjdVODQ5cVJJLWt4dk9vZFBScVp2ZmpzQXZZRy1ncDM5c2tRbXBVVHVrQnpmMGVrQXNkQVItV3h4dVQ1V1BTbjhnM3k2ZUdPdnhVOFk1NmllNTZkdGJTbW9NX0k5U3E2Tkk?oc=5"
+#     decoded_url = decode_google_news_url(source_url)
+#     print(decoded_url)

googlenewsdecoder-0.1.0.dist-info/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2024 Sujit Biswas
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

googlenewsdecoder-0.1.0.dist-info/METADATA

@@ -0,0 +1,53 @@
+Metadata-Version: 2.1
+Name: googlenewsdecoder
+Version: 0.1.0
+Summary: A package to decode Google News URLs.
+Home-page: https://github.com/SSujitX/google-news-url-decoder
+Author: Sujit Biswas
+Author-email: ssujitxx@example.com
+License: MIT
+Classifier: Programming Language :: Python :: 3
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Requires-Python: >=3.9
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: requests
+
+# Google News Decoder
+
+A Python package to decode Google News URLs.
+
+## Installation
+
+You can install this package using pip:
+
+```sh
+pip install googlenewsdecoder
+```
+
+## Credits
+
+Original script by [huksley](https://gist.github.com/huksley/bc3cb046157a99cd9d1)
+
+## Usage
+
+Here is an example of how to use this package:
+
+```python
+
+from googlenewsdecoder import decoderv1, decoderv2
+
+if __name__ == "__main__":
+    # source_url = "https://news.google.com/rss/articles/CBMiLmh0dHBzOi8vd3d3LmJiYy5jb20vbmV3cy9hcnRpY2xlcy9jampqbnhkdjE4OG_SATJodHRwczovL3d3dy5iYmMuY29tL25ld3MvYXJ0aWNsZXMvY2pqam54ZHYxODhvLmFtcA?oc=5"
+    # source_url = "https://news.google.com/rss/articles/CBMiVkFVX3lxTE4zaGU2bTY2ZGkzdTRkSkJ0cFpsTGlDUjkxU2FBRURaTWU0c3QzVWZ1MHZZNkZ5Vzk1ZVBnTDFHY2R6ZmdCUkpUTUJsS1pqQTlCRzlzbHV3?oc=5"
+    source_url = "https://news.google.com/rss/articles/CBMiqwFBVV95cUxNMTRqdUZpNl9hQldXbGo2YVVLOGFQdkFLYldlMUxUVlNEaElsYjRRODVUMkF3R1RYdWxvT1NoVzdUYS0xSHg3eVdpTjdVODQ5cVJJLWt4dk9vZFBScVp2ZmpzQXZZRy1ncDM5c2tRbXBVVHVrQnpmMGVrQXNkQVItV3h4dVQ1V1BTbjhnM3k2ZUdPdnhVOFk1NmllNTZkdGJTbW9NX0k5U3E2Tkk?oc=5"
+    # Decode the URL using decoderv1
+    decoded_url_v1 = decoderv1(source_url)
+    print(decoded_url_v1)
+
+    # Decode the URL using decoderv2
+    decoded_url_v2 = decoderv2(source_url)
+    print(decoded_url_v2)
+    print(decoded_url)
+```

googlenewsdecoder-0.1.0.dist-info/RECORD

@@ -0,0 +1,8 @@
+googlenewsdecoder/__init__.py,sha256=9akr_IrkwaJ7qt0NnccM_sNP-9F4-cljW-ni7wimNvU,120
+googlenewsdecoder/decoderv1.py,sha256=EvkeNEJ_CWdQSubJYYZ4Ck5sJuhMOUBYl-l_UsRGXpE,1398
+googlenewsdecoder/decoderv2.py,sha256=8rKw17Jfaex-WIzkUkJrNtrEntNMYJ-3o_IfFMpArkM,3147
+googlenewsdecoder-0.1.0.dist-info/LICENSE,sha256=MeNpaB__quLl2z10dJqSfp_-U4idVkEHk44wgVrZUdY,1090
+googlenewsdecoder-0.1.0.dist-info/METADATA,sha256=D713Mqm0_RwQ7bjl1o9y3-EArX7QNIwvuMbUusJBxo4,1882
+googlenewsdecoder-0.1.0.dist-info/WHEEL,sha256=HiCZjzuy6Dw0hdX5R3LCFPDmFS4BWl8H-8W39XfmgX4,91
+googlenewsdecoder-0.1.0.dist-info/top_level.txt,sha256=fJXKsRv68x7e2pnNLLBqwz5o1Lws3-RnG60mru-Yuh4,18
+googlenewsdecoder-0.1.0.dist-info/RECORD,,

googlenewsdecoder-0.1.0.dist-info/WHEEL

@@ -0,0 +1,5 @@
+Wheel-Version: 1.0
+Generator: setuptools (72.2.0)
+Root-Is-Purelib: true
+Tag: py3-none-any
+

googlenewsdecoder-0.1.0.dist-info/top_level.txt

@@ -0,0 +1 @@
+googlenewsdecoder