gecko-web-runtime-client 1.4.3__tar.gz → 1.4.4__tar.gz

{gecko_web_runtime_client-1.4.3 → gecko_web_runtime_client-1.4.4}/PACKAGE_README.md

@@ -19,11 +19,11 @@ HTTP imports are retained through `wpr-http`.
 
 The same distribution includes `gecko_web_runtime.integrations.wechat`.
 It uses `wpr-http` and a local Node.js environment, with no browser Page.
-Install version 1.4.3 or newer with its optional dependencies, then prepare Node.js
+Install version 1.4.4 or newer with its optional dependencies, then prepare Node.js
 20+ dependencies in the user's cache:
 
 ```powershell
-pip install --upgrade "gecko-web-runtime-client[wechat]>=1.4.3"
+pip install --upgrade "gecko-web-runtime-client[wechat]>=1.4.4"
 python -m gecko_web_runtime.integrations.wechat install-js
 ```
 

{gecko_web_runtime_client-1.4.3 → gecko_web_runtime_client-1.4.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: gecko-web-runtime-client
-Version: 1.4.3
+Version: 1.4.4
 Summary: Thin Python client for the Firefox-derived WPR Gecko Worker protocol
 Author: WPR project
 License: MPL-2.0-compatible client; see the runtime bundle notices
@@ -40,11 +40,11 @@ HTTP imports are retained through `wpr-http`.
 
 The same distribution includes `gecko_web_runtime.integrations.wechat`.
 It uses `wpr-http` and a local Node.js environment, with no browser Page.
-Install version 1.4.3 or newer with its optional dependencies, then prepare Node.js
+Install version 1.4.4 or newer with its optional dependencies, then prepare Node.js
 20+ dependencies in the user's cache:
 
 ```powershell
-pip install --upgrade "gecko-web-runtime-client[wechat]>=1.4.3"
+pip install --upgrade "gecko-web-runtime-client[wechat]>=1.4.4"
 python -m gecko_web_runtime.integrations.wechat install-js
 ```
 

{gecko_web_runtime_client-1.4.3 → gecko_web_runtime_client-1.4.4}/gecko_web_runtime/integrations/__init__.py

@@ -1 +1 @@
-"""Optional site integrations shipped with the browser client."""
+"""Optional site integrations shipped with the browser client."""

{gecko_web_runtime_client-1.4.3 → gecko_web_runtime_client-1.4.4}/gecko_web_runtime/integrations/wechat/__init__.py

@@ -1,12 +1,12 @@
-"""HTTP and local-JavaScript WeChat article client."""
-
-from .client import AsyncWechatClient
-from .exceptions import WechatDependencyError
-from .models import WechatArticle, WechatConfig
-
-__all__ = [
-    "AsyncWechatClient",
-    "WechatArticle",
-    "WechatConfig",
-    "WechatDependencyError",
-]
+"""HTTP and local-JavaScript WeChat article client."""
+
+from .client import AsyncWechatClient
+from .exceptions import WechatDependencyError
+from .models import WechatArticle, WechatConfig
+
+__all__ = [
+    "AsyncWechatClient",
+    "WechatArticle",
+    "WechatConfig",
+    "WechatDependencyError",
+]

{gecko_web_runtime_client-1.4.3 → gecko_web_runtime_client-1.4.4}/gecko_web_runtime/integrations/wechat/__main__.py

@@ -1,23 +1,23 @@
-"""Install optional Node dependencies into the user's WPR cache."""
-
-import argparse
-
-from .js_runtime.runtime import LocalJsRuntime
-from .models import WechatConfig
-
-
-def main():
-    parser = argparse.ArgumentParser()
-    parser.add_argument("command", choices=["install-js"])
-    parser.add_argument("--cache-dir")
-    parser.add_argument("--node", default="node")
-    args = parser.parse_args()
-    runtime = LocalJsRuntime(
-        WechatConfig(js_cache_dir=args.cache_dir, node_executable=args.node)
-    )
-    print(runtime.install())
-    return 0
-
-
-if __name__ == "__main__":
-    raise SystemExit(main())
+"""Install optional Node dependencies into the user's WPR cache."""
+
+import argparse
+
+from .js_runtime.runtime import LocalJsRuntime
+from .models import WechatConfig
+
+
+def main():
+    parser = argparse.ArgumentParser()
+    parser.add_argument("command", choices=["install-js"])
+    parser.add_argument("--cache-dir")
+    parser.add_argument("--node", default="node")
+    args = parser.parse_args()
+    runtime = LocalJsRuntime(
+        WechatConfig(js_cache_dir=args.cache_dir, node_executable=args.node)
+    )
+    print(runtime.install())
+    return 0
+
+
+if __name__ == "__main__":
+    raise SystemExit(main())

{gecko_web_runtime_client-1.4.3 → gecko_web_runtime_client-1.4.4}/gecko_web_runtime/integrations/wechat/_article.py

@@ -1,110 +1,110 @@
-"""Article parsing without a Node dependency or a hard-coded article ID."""
-
-from html.parser import HTMLParser
-import hashlib
-import re
-from urllib.parse import parse_qs, urlsplit
-
-
-class ArticleParser(HTMLParser):
-    def __init__(self):
-        super().__init__(convert_charrefs=True)
-        self.stack = []
-        self.title = []
-        self.content = []
-        self.media = []
-        self.body_found = False
-
-    def handle_starttag(self, tag, attrs):
-        values = dict(attrs)
-        title = values.get("id") == "activity-name" or any(x[1] for x in self.stack)
-        body = values.get("id") == "js_content" or any(x[2] for x in self.stack)
-        self.body_found |= values.get("id") == "js_content"
-        skip = tag in {"script", "style"} or any(x[3] for x in self.stack)
-        if body and tag in {
-            "img",
-            "iframe",
-            "video",
-            "mp-video",
-            "mp-common-videosnap",
-        }:
-            self.media.append(
-                {
-                    "tag": tag,
-                    "src": values.get("data-src") or values.get("src", ""),
-                    "vid": values.get("vid") or values.get("data-vid", ""),
-                }
-            )
-        if body and tag in {"p", "section", "br", "h1", "h2"}:
-            self.content.append("\n")
-        if tag not in {
-            "area",
-            "base",
-            "br",
-            "col",
-            "embed",
-            "hr",
-            "img",
-            "input",
-            "link",
-            "meta",
-            "param",
-            "source",
-            "track",
-            "wbr",
-        }:
-            self.stack.append((tag, title, body, skip))
-
-    def handle_startendtag(self, tag, attrs):
-        self.handle_starttag(tag, attrs)
-        self.handle_endtag(tag)
-
-    def handle_endtag(self, tag):
-        for index in range(len(self.stack) - 1, -1, -1):
-            if self.stack[index][0] == tag:
-                if self.stack[index][2] and tag in {"p", "section", "h1", "h2"}:
-                    self.content.append("\n")
-                del self.stack[index:]
-                break
-
-    def handle_data(self, data):
-        if not self.stack or self.stack[-1][3]:
-            return
-        if self.stack[-1][1]:
-            self.title.append(data)
-        if self.stack[-1][2]:
-            self.content.append(data)
-
-
-def parse_article(html, url):
-    parser = ArticleParser()
-    parser.feed(html)
-    title = " ".join("".join(parser.title).split())
-    text = re.sub(
-        r"\n\s*\n+", "\n\n", re.sub(r"[ \t]+", " ", "".join(parser.content))
-    ).strip()
-    query = parse_qs(urlsplit(url).query)
-    identity = {
-        f"target_{key}_matches": query[key][0] in html if query.get(key) else None
-        for key in ("mid", "sn")
-    }
-    verified = (
-        bool(title)
-        and parser.body_found
-        and (len(text) > 100 or bool(parser.media))
-        and not re.search(r"register_code\s*:", html)
-        and all(value is not False for value in identity.values())
-    )
-    proof = {
-        "title": title,
-        "content_chars": len(text),
-        "media_count": len(parser.media),
-        "media": parser.media,
-        "html_bytes": len(html.encode("utf-8")),
-        "html_sha256": hashlib.sha256(html.encode("utf-8")).hexdigest(),
-        "article_verified": verified,
-        **identity,
-    }
-    if not verified:
-        raise ValueError("Article title/body/target identity verification failed")
-    return proof, text
+"""Article parsing without a Node dependency or a hard-coded article ID."""
+
+from html.parser import HTMLParser
+import hashlib
+import re
+from urllib.parse import parse_qs, urlsplit
+
+
+class ArticleParser(HTMLParser):
+    def __init__(self):
+        super().__init__(convert_charrefs=True)
+        self.stack = []
+        self.title = []
+        self.content = []
+        self.media = []
+        self.body_found = False
+
+    def handle_starttag(self, tag, attrs):
+        values = dict(attrs)
+        title = values.get("id") == "activity-name" or any(x[1] for x in self.stack)
+        body = values.get("id") == "js_content" or any(x[2] for x in self.stack)
+        self.body_found |= values.get("id") == "js_content"
+        skip = tag in {"script", "style"} or any(x[3] for x in self.stack)
+        if body and tag in {
+            "img",
+            "iframe",
+            "video",
+            "mp-video",
+            "mp-common-videosnap",
+        }:
+            self.media.append(
+                {
+                    "tag": tag,
+                    "src": values.get("data-src") or values.get("src", ""),
+                    "vid": values.get("vid") or values.get("data-vid", ""),
+                }
+            )
+        if body and tag in {"p", "section", "br", "h1", "h2"}:
+            self.content.append("\n")
+        if tag not in {
+            "area",
+            "base",
+            "br",
+            "col",
+            "embed",
+            "hr",
+            "img",
+            "input",
+            "link",
+            "meta",
+            "param",
+            "source",
+            "track",
+            "wbr",
+        }:
+            self.stack.append((tag, title, body, skip))
+
+    def handle_startendtag(self, tag, attrs):
+        self.handle_starttag(tag, attrs)
+        self.handle_endtag(tag)
+
+    def handle_endtag(self, tag):
+        for index in range(len(self.stack) - 1, -1, -1):
+            if self.stack[index][0] == tag:
+                if self.stack[index][2] and tag in {"p", "section", "h1", "h2"}:
+                    self.content.append("\n")
+                del self.stack[index:]
+                break
+
+    def handle_data(self, data):
+        if not self.stack or self.stack[-1][3]:
+            return
+        if self.stack[-1][1]:
+            self.title.append(data)
+        if self.stack[-1][2]:
+            self.content.append(data)
+
+
+def parse_article(html, url):
+    parser = ArticleParser()
+    parser.feed(html)
+    title = " ".join("".join(parser.title).split())
+    text = re.sub(
+        r"\n\s*\n+", "\n\n", re.sub(r"[ \t]+", " ", "".join(parser.content))
+    ).strip()
+    query = parse_qs(urlsplit(url).query)
+    identity = {
+        f"target_{key}_matches": query[key][0] in html if query.get(key) else None
+        for key in ("mid", "sn")
+    }
+    verified = (
+        bool(title)
+        and parser.body_found
+        and (len(text) > 100 or bool(parser.media))
+        and not re.search(r"register_code\s*:", html)
+        and all(value is not False for value in identity.values())
+    )
+    proof = {
+        "title": title,
+        "content_chars": len(text),
+        "media_count": len(parser.media),
+        "media": parser.media,
+        "html_bytes": len(html.encode("utf-8")),
+        "html_sha256": hashlib.sha256(html.encode("utf-8")).hexdigest(),
+        "article_verified": verified,
+        **identity,
+    }
+    if not verified:
+        raise ValueError("Article title/body/target identity verification failed")
+    return proof, text