ForageFacebook 2.1.0__tar.gz → 2.3.0__tar.gz

{foragefacebook-2.1.0 → foragefacebook-2.3.0}/.github/workflows/ci.yml

@@ -16,26 +16,6 @@ concurrency:
   cancel-in-progress: ${{ github.ref_type != 'tag' }}
 
 jobs:
-  test:
-    name: test (${{ matrix.python-version }})
-    runs-on: ubuntu-latest
-    timeout-minutes: 15
-    strategy:
-      fail-fast: false
-      matrix:
-        python-version: ["3.10", "3.14"]
-    steps:
-      - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1  # v7.0.1
-        with:
-          persist-credentials: false
-      - uses: astral-sh/setup-uv@bec219d24cd3e171d82865faccec33120bb574f4  # v10.1.0
-        with:
-          version: "0.12.17"
-          python-version: ${{ matrix.python-version }}
-      - run: uv sync --locked --all-extras --no-config
-      - run: uv run --locked --no-config playwright install --with-deps chromium
-      - run: uv run --locked --no-config pytest tests/ -q
-
   quality:
     runs-on: ubuntu-latest
     timeout-minutes: 15
@@ -51,8 +31,8 @@ jobs:
       - name: Check source and lockfile
         run: |
           uv lock --check --no-config
-          uv run --locked --no-config ruff check src/ tests/
-          uv run --locked --no-config ruff format --check src/ tests/
+          uv run --locked --no-config ruff check src/ scripts/
+          uv run --locked --no-config ruff format --check src/ scripts/
           uv run --locked --no-config ty check src/forage/
       - name: Audit workflows and release helper
         run: |
@@ -70,12 +50,11 @@ jobs:
 
   check:
     if: always()
-    needs: [test, quality]
+    needs: [quality]
     runs-on: ubuntu-latest
     timeout-minutes: 2
     steps:
       - name: Require all checks
         env:
-          TEST_RESULT: ${{ needs.test.result }}
           QUALITY_RESULT: ${{ needs.quality.result }}
-        run: test "$TEST_RESULT" = success && test "$QUALITY_RESULT" = success
+        run: test "$QUALITY_RESULT" = success

{foragefacebook-2.1.0 → foragefacebook-2.3.0}/.gitignore

@@ -60,3 +60,8 @@ output/
 .env
 .env.local
 .env.*.local
+
+# CLI end-to-end runner
+/node_modules/
+/.e2e/
+!package-lock.json

foragefacebook-2.3.0/.python-version

@@ -0,0 +1 @@
+3.14

{foragefacebook-2.1.0 → foragefacebook-2.3.0}/AGENTS.md

@@ -12,11 +12,11 @@ Forage is a CLI tool for scraping private Facebook groups to analyze community d
 uv sync                              # Install deps (always use uv, not pip/python)
 uv run forage --help                 # Run CLI
 uv run ty check src/                 # Type check (Astral's ty)
-uv run pytest                        # Run all tests
-uv run pytest tests/test_parser.py   # Run a single test file
-uv run pytest -k "test_name"         # Run a single test by name
-uv run ruff check src/ tests/        # Lint
-uv run ruff format src/ tests/       # Auto-format (CI enforces this)
+make check                           # Lint, type check, and build
+make test                            # Read-only live Facebook checks
+make pre-pr                          # Static and live checks; set FORAGE_E2E_GROUP
+uv run ruff check src/ scripts/       # Lint
+uv run ruff format src/ scripts/      # Format
 ```
 
 ## Manual Testing
@@ -59,7 +59,12 @@ Random viewport sizes, `human_delay()` with variance, real Chromium browser, ses
 
 ### Test Structure
 
-Tests in `tests/` with HTML fixtures in `tests/fixtures/` (realistic Facebook HTML snippets). `conftest.py` loads fixtures into real Playwright Chromium pages with network access blocked. Install Chromium before tests.
+Use `make test` for real CLI reads through the saved Facebook session. Install Chromium first.
+Set `FORAGE_E2E_GROUP` to test a group; otherwise the test searches Marketplace for computers.
+Before you create a PR, run `FORAGE_E2E_GROUP=<active-group> make pre-pr`.
+Set `FORAGE_E2E_UNTIL=YYYY-MM-DD` to also check a historical window with known posts.
+Keep unit tests, mock tests, and fake-server suites out of this repo. CI runs static checks and package builds.
+Live tests must not log in, change credentials, or write to Facebook.
 
 ## Fragile Code — Check Here First When Things Break
 
@@ -99,7 +104,7 @@ Steps:
 1. Update `version` in both `pyproject.toml` and `src/forage/__init__.py`
 2. Run `uv lock --no-config` — refresh locked editable package metadata without leaking user-level uv settings
 3. Update `CHANGELOG.md` — add version section under `## [Unreleased]`, update comparison links at bottom
-4. Run `uv lock --check --no-config` and `uv run ruff format src/ tests/` — CI enforces formatting
+4. Run `uv lock --check --no-config` and `uv run ruff format src/ scripts/` — CI enforces formatting
 5. Commit: `git commit -m "chore: release vX.Y.Z"`
 6. Push a feature branch and open a PR. Merge only after all required checks pass. Never push directly to `master`.
 7. Tag: `git tag -a vX.Y.Z -m "Release vX.Y.Z"` then `git push origin vX.Y.Z`

{foragefacebook-2.1.0 → foragefacebook-2.3.0}/CHANGELOG.md

@@ -7,6 +7,37 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+## [2.3.0] - 2026-11-03
+
+### Added
+
+- Add Marketplace sort choices and support more currency-symbol price formats, inspired by PR #50.
+- Add local `make pre-pr` checks for live Marketplace sorts, group comments, date windows, and saved exports.
+
+### Fixed
+
+- Preserve comment nesting and remove the fallback that treats arbitrary post text as comments.
+- Read relative comment-author links and restrict permalink comments to the requested post.
+- Continue historical searches past newer posts and include posts labeled "Just now" at the default cutoff.
+- Parse compact reaction totals and recognize `multi_permalinks` post links.
+- Skip repeated Marketplace candidates before text parsing and stop before an unnecessary final group scroll.
+- Convert the CLI's miles to Facebook's kilometer radius and use the verified nearest-first sort value.
+- Select Python 3.14 for local development, matching CI.
+
+### Thanks
+
+- Thanks to [@kha-faz](https://github.com/kha-faz) for the currency and Marketplace sort contributions in [PR #50](https://github.com/jwmoss/forage/pull/50).
+
+## [2.2.0] - 2026-10-10
+
+### Changed
+
+- Replace unit and synthetic browser tests with read-only live CLI checks.
+- Keep lint, type checks, and package build/install checks in CI.
+- Remove pytest and the Node test harness.
+- Add common `make check`, `make test`, and `make build` entry points.
+- Add `forage version` beside the existing `--version` flag.
+
 ## [2.1.0] - 2026-09-20
 
 ### Fixed
@@ -237,7 +268,9 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - Sensitive files excluded via `.gitignore`
 - Security guidelines in SECURITY.md
 
-[Unreleased]: https://github.com/jwmoss/forage/compare/v2.1.0...HEAD
+[Unreleased]: https://github.com/jwmoss/forage/compare/v2.3.0...HEAD
+[2.3.0]: https://github.com/jwmoss/forage/compare/v2.2.0...v2.3.0
+[2.2.0]: https://github.com/jwmoss/forage/compare/v2.1.0...v2.2.0
 [2.1.0]: https://github.com/jwmoss/forage/compare/v2.0.0...v2.1.0
 [2.0.0]: https://github.com/jwmoss/forage/compare/v1.2.1...v2.0.0
 [1.2.1]: https://github.com/jwmoss/forage/compare/v1.2.0...v1.2.1

{foragefacebook-2.1.0 → foragefacebook-2.3.0}/CONTRIBUTING.md

@@ -22,7 +22,8 @@ Thank you for your interest in contributing to Forage!
 
 4. Run tests:
    ```bash
-   uv run pytest tests/ -v
+   make check
+   make test
    ```
 
 5. Run type checker:
@@ -55,17 +56,26 @@ Example: `feat: add SQLite export option`
 1. Fork the repository
 2. Create a feature branch (`git checkout -b feat/my-feature`)
 3. Make your changes
-4. Ensure tests pass (`uv run pytest tests/`)
+4. Run the local PR checks with a saved session:
+   ```bash
+   FORAGE_E2E_GROUP=your-group-slug FORAGE_E2E_UNTIL=YYYY-MM-DD make pre-pr
+   ```
+   Select an active group with visible reply threads and a historical window with known posts.
+   `FORAGE_E2E_UNTIL` is optional. It tests the seven days before the selected inclusive end date.
 5. Ensure type checking passes (`uv run ty check src/forage/`)
 6. Commit with a descriptive message
 7. Push and open a pull request
 
 ## Testing
 
-- Write tests for new functionality
-- Use pytest fixtures for common test data
-- Mock external dependencies (Playwright, network)
-- Aim for good coverage of edge cases
+- Verify behavior through the real CLI against Facebook.
+- Keep live checks read-only and use the existing session.
+- Do not add unit tests, mock tests, or fake-server suites.
+- Run `make test-marketplace` to check all five sort orders against Facebook's selected controls.
+- Run `FORAGE_E2E_GROUP=your-group-slug make test-group` to check posts, comments, and real-data exports.
+- Run `make pre-pr` with the group variables above before you create a PR.
+- Keep session files and private records out of commits and PR descriptions.
+- Live checks need suitable records. A passing run does not prove rare cases that the live pages do not contain.
 
 ## Reporting Issues
 

foragefacebook-2.3.0/Makefile

@@ -0,0 +1,25 @@
+.PHONY: check test test-marketplace test-group test-all pre-pr build
+
+check:
+	uv lock --check --no-config
+	uv run --locked --no-config ruff check src/ scripts/
+	uv run --locked --no-config ruff format --check src/ scripts/
+	uv run --locked --no-config ty check src/forage/
+	uv build --no-config
+
+test:
+	uv run --locked --no-config python scripts/live-e2e.py
+
+test-marketplace:
+	env -u FORAGE_E2E_GROUP uv run --locked --no-config python scripts/live-e2e.py
+
+test-group:
+	@test -n "$$FORAGE_E2E_GROUP" || { echo 'Set FORAGE_E2E_GROUP to an active group you can access.' >&2; exit 2; }
+	uv run --locked --no-config python scripts/live-e2e.py
+
+test-all: test-marketplace test-group
+
+pre-pr: check test-all
+
+build:
+	uv build --no-config

{foragefacebook-2.1.0 → foragefacebook-2.3.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.5
 Name: ForageFacebook
-Version: 2.1.0
+Version: 2.3.0
 Summary: CLI tool to scrape posts, comments, and reactions from private Facebook groups
 Project-URL: Homepage, https://github.com/jwmoss/forage
 Project-URL: Repository, https://github.com/jwmoss/forage
@@ -28,7 +28,6 @@ Requires-Dist: playwright>=1.40
 Requires-Dist: pydantic>=2.0
 Requires-Dist: rich>=13.0
 Provides-Extra: dev
-Requires-Dist: pytest>=8.0; extra == 'dev'
 Requires-Dist: ruff>=0.8; extra == 'dev'
 Requires-Dist: ty>=0.0.1a6; extra == 'dev'
 Description-Content-Type: text/markdown
@@ -178,11 +177,19 @@ Commands:
 
 ```bash
 uv run forage marketplace "rtx 4070" --city wilmington --radius 40 --limit 20 -o listings.json
+uv run forage marketplace "computer" --sort-by price_ascend
 ```
 
 `--limit` counts accepted listings. `--max-candidates` bounds the search cost, including rejected candidates; its default is 200.
 Forage excludes distant listings and listings whose coordinates it cannot verify. City is the search center, not a city-only filter.
-The current parser supports electronics with dollar prices or “Free” labels. Search relevance follows Facebook's results.
+The parser accepts “Free” and prices with `$`, `£`, `€`, `¥`, `₹`, `₩`, or `₽` symbols.
+It accepts prefixes such as `CA$` and `R$`, trailing symbols such as `80 €`, and space-separated digits.
+Prices remain display strings. Currency conversion, currency-code-only prices, and localized free labels are unsupported.
+Search relevance follows Facebook's results.
+
+`--sort-by` accepts `creation_time_descend` (default), `suggested`, `price_ascend`, `price_descend`, or `distance_ascend`.
+These values request Facebook's sort order. They do not sort the collected subset locally.
+The CLI radius uses miles; Forage converts it to kilometers for Facebook's search URL.
 
 ### Local diagnosis and saved exports
 
@@ -319,13 +326,32 @@ uv sync --extra dev
 # Run type checker
 uv run ty check src/
 
-# Install Chromium for offline DOM tests
+# Run static checks and build the package
+make check
+
+# Install Chromium for live reads
 uv run playwright install chromium
 
-# Run tests; browser fixtures block network access
-uv run pytest
+# Read Marketplace through the saved Facebook session
+make test
+
+# Read posts and comments from an active group you can access
+FORAGE_E2E_GROUP=your-group-slug make test
+
+# Run static checks, all Marketplace sorts, group comments, and saved exports before a PR
+FORAGE_E2E_GROUP=your-group-slug make pre-pr
+
+# Also check a historical window with known posts (seven days through the inclusive end date)
+FORAGE_E2E_GROUP=your-group-slug FORAGE_E2E_UNTIL=2026-10-29 make pre-pr
 ```
 
+Live tests run the real CLI and Facebook pages. They do not use fixtures or mock servers.
+They need an existing login session. CI runs static checks and package build/install checks.
+Group checks require an active group with visible reply threads. The checks use temporary local files for exports.
+Marketplace checks confirm Facebook's selected sort control for each CLI result URL.
+Live data changes. These checks do not cover a rare parser case unless the selected pages contain it.
+
+
 ## Architecture
 
 ```
@@ -344,12 +370,12 @@ src/forage/
 - Rate limiting may require slower scraping
 - Individual reaction types not broken out (only total)
 - Session lifetime depends on Facebook; use `forage login` when authentication fails
-- English page labels and supported DOM fixtures define the tested parser scope
+- English page labels define the supported parser scope
 - Previously overwritten SQLite comments require a new scrape; upgrades cannot recover them
 
 ## Roadmap
 
-Prioritize sanitized DOM fixtures and verified selector updates. Add incremental collection only after identity and completeness checks support it.
+Prioritize read-only live regression checks and verified selector updates. Add incremental collection only after identity and completeness checks support it.
 Use shell loops for batches, system scheduling for recurring commands, and SQLite or jq for analysis.
 
 ### Contributing

{foragefacebook-2.1.0 → foragefacebook-2.3.0}/README.md

@@ -143,11 +143,19 @@ Commands:
 
 ```bash
 uv run forage marketplace "rtx 4070" --city wilmington --radius 40 --limit 20 -o listings.json
+uv run forage marketplace "computer" --sort-by price_ascend
 ```
 
 `--limit` counts accepted listings. `--max-candidates` bounds the search cost, including rejected candidates; its default is 200.
 Forage excludes distant listings and listings whose coordinates it cannot verify. City is the search center, not a city-only filter.
-The current parser supports electronics with dollar prices or “Free” labels. Search relevance follows Facebook's results.
+The parser accepts “Free” and prices with `$`, `£`, `€`, `¥`, `₹`, `₩`, or `₽` symbols.
+It accepts prefixes such as `CA$` and `R$`, trailing symbols such as `80 €`, and space-separated digits.
+Prices remain display strings. Currency conversion, currency-code-only prices, and localized free labels are unsupported.
+Search relevance follows Facebook's results.
+
+`--sort-by` accepts `creation_time_descend` (default), `suggested`, `price_ascend`, `price_descend`, or `distance_ascend`.
+These values request Facebook's sort order. They do not sort the collected subset locally.
+The CLI radius uses miles; Forage converts it to kilometers for Facebook's search URL.
 
 ### Local diagnosis and saved exports
 
@@ -284,13 +292,32 @@ uv sync --extra dev
 # Run type checker
 uv run ty check src/
 
-# Install Chromium for offline DOM tests
+# Run static checks and build the package
+make check
+
+# Install Chromium for live reads
 uv run playwright install chromium
 
-# Run tests; browser fixtures block network access
-uv run pytest
+# Read Marketplace through the saved Facebook session
+make test
+
+# Read posts and comments from an active group you can access
+FORAGE_E2E_GROUP=your-group-slug make test
+
+# Run static checks, all Marketplace sorts, group comments, and saved exports before a PR
+FORAGE_E2E_GROUP=your-group-slug make pre-pr
+
+# Also check a historical window with known posts (seven days through the inclusive end date)
+FORAGE_E2E_GROUP=your-group-slug FORAGE_E2E_UNTIL=2026-10-29 make pre-pr
 ```
 
+Live tests run the real CLI and Facebook pages. They do not use fixtures or mock servers.
+They need an existing login session. CI runs static checks and package build/install checks.
+Group checks require an active group with visible reply threads. The checks use temporary local files for exports.
+Marketplace checks confirm Facebook's selected sort control for each CLI result URL.
+Live data changes. These checks do not cover a rare parser case unless the selected pages contain it.
+
+
 ## Architecture
 
 ```
@@ -309,12 +336,12 @@ src/forage/
 - Rate limiting may require slower scraping
 - Individual reaction types not broken out (only total)
 - Session lifetime depends on Facebook; use `forage login` when authentication fails
-- English page labels and supported DOM fixtures define the tested parser scope
+- English page labels define the supported parser scope
 - Previously overwritten SQLite comments require a new scrape; upgrades cannot recover them
 
 ## Roadmap
 
-Prioritize sanitized DOM fixtures and verified selector updates. Add incremental collection only after identity and completeness checks support it.
+Prioritize read-only live regression checks and verified selector updates. Add incremental collection only after identity and completeness checks support it.
 Use shell loops for batches, system scheduling for recurring commands, and SQLite or jq for analysis.
 
 ### Contributing

{foragefacebook-2.1.0 → foragefacebook-2.3.0}/docs/capabilities.md

@@ -1,16 +1,16 @@
 # Forage capability contract
 
-Updated: 2026-09-20. This file describes the tested application behavior, not exhaustive Facebook coverage.
+Updated: 2026-11-03. This file describes observed application behavior, not exhaustive Facebook coverage.
 
 | Surface | Verified locally | Known limits |
 | --- | --- | --- |
 | Login | Browser state storage with owner-only POSIX permissions | Manual Facebook login; session validity requires Facebook access |
 | Doctor | Browser executable, session existence, permission checks | No session contents read; no browser launch; no network check |
-| Group posts | Supported HTML fixtures, full visible paragraphs, nested-comment exclusion, supported expansion controls, permalinks | English labels; Facebook layout changes; media and attachment extraction absent |
+| Group posts | Live authenticated CLI reads with native post IDs and known timestamps | English labels; Facebook layout changes; media and attachment extraction absent |
 | Dates | Inclusive calendar end dates, reversed-range rejection, relative timestamp parsing | Local system/browser timezone; month/year relative times remain approximate |
-| Comments | Native IDs, fallback IDs scoped to posts, supported reply collection | All-comment coverage remains unverified; identical fallback comments within one post can collide; comment timestamps remain unknown |
+| Comments | Live native IDs, relative author links, and reply-parent relationships; fallback IDs scoped to posts | All-comment coverage remains unverified; identical fallback comments within one post can collide; comment timestamps remain unknown |
 | Reactions | Supported total-count labels | Missing and skipped counts retain legacy zero defaults; no promise of complete per-type counts |
-| Marketplace | Electronics, dollar/free prices, title/location, accepted result limit, strict radius check bound to the requested listing ID | Fixed category; fuzzy Facebook relevance; approximate coordinates; unbound or invalid coordinates are excluded; no exhaustive search guarantee |
+| Marketplace | Live listings and all five selected sort controls; mile-to-kilometer URL conversion; strict radius check bound to the requested listing ID | Fixed category; fuzzy Facebook relevance; approximate coordinates; unbound or invalid coordinates are excluded; no exhaustive search guarantee |
 | Export | Group JSON to JSON, LLM JSON, CSV, SQLite without login | Keep original JSON for diagnostics; old overwritten comments cannot be recovered automatically |
 
 ## Result diagnostics
@@ -30,8 +30,19 @@ Meta's [Content Library announcement](https://about.fb.com/news/2023/11/new-tool
 It does not establish private-group or general personal Marketplace API access.
 
 The [Graph API v19 changelog](https://developers.facebook.com/docs/graph-api/changelog/version19.0/) is the authority for historical Groups API removal.
-The current audit cannot retrieve that page or current [Marketplace documentation](https://developers.facebook.com/docs/marketplace/) because Meta returns 429 responses.
-Current replacement availability and exhaustive REST coverage therefore remain unknown. Do not infer private APIs from DOM fields.
+The September 2026 audit cannot retrieve that page or the [Marketplace documentation](https://developers.facebook.com/docs/marketplace/) because Meta returns 429 responses.
+This update does not recheck replacement API availability. Do not infer private APIs from DOM fields.
 
-All new selector checks use synthetic, network-blocked Chromium pages. No live authenticated Facebook session validates this change.
-Use sanitized fixtures from a confirmed failure before changing selectors. Never publish session state or private group content in test fixtures.
+## Local regression checks
+
+Run `FORAGE_E2E_GROUP=<active-group> FORAGE_E2E_UNTIL=YYYY-MM-DD make pre-pr` before a PR.
+The date is optional. Select a historical window with known posts.
+The checks use the saved session and real CLI reads. They require visible reply threads and verify Facebook's selected sort controls,
+post/comment records, and CSV/SQLite exports of the collected data. CI remains static and does not use Facebook credentials.
+
+On November 3, the same historical request returns zero posts on the base revision after nine rejected newer posts.
+The fix reaches a matching post after 63 newer candidates. Live group, export, and all five Marketplace sort checks pass.
+Direct parser checks cover the default "Just now" cutoff, compact reaction counts, and supported currency-symbol forms.
+Those direct checks do not establish live coverage for every rare label or locale.
+
+Never publish session state or private group content.

{foragefacebook-2.1.0 → foragefacebook-2.3.0}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "ForageFacebook"
-version = "2.1.0"
+version = "2.3.0"
 description = "CLI tool to scrape posts, comments, and reactions from private Facebook groups"
 readme = "README.md"
 requires-python = ">=3.10"
@@ -42,7 +42,6 @@ Changelog = "https://github.com/jwmoss/forage/blob/master/CHANGELOG.md"
 
 [project.optional-dependencies]
 dev = [
-    "pytest>=8.0",
     "ruff>=0.8",
     "ty>=0.0.1a6",
 ]

foragefacebook-2.3.0/scripts/live-e2e.py

@@ -0,0 +1,164 @@
+#!/usr/bin/env python3
+"""Check real Facebook reads and exports through the CLI and saved session."""
+
+from __future__ import annotations
+
+import csv
+import json
+import os
+import re
+import shlex
+import sqlite3
+import subprocess
+import sys
+import tempfile
+from datetime import date, datetime, timedelta
+from pathlib import Path
+
+from playwright.sync_api import sync_playwright
+
+SORT_LABELS = {
+    "creation_time_descend": "Date listed: Newest first",
+    "suggested": "Suggested",
+    "price_ascend": "Price: Lowest first",
+    "price_descend": "Price: Highest first",
+    "distance_ascend": "Distance: Nearest first",
+}
+
+
+def call(*args: str) -> dict:
+    """Run the real CLI without exposing private records on failure."""
+    cli = shlex.split(os.environ.get("FORAGE_BIN", "forage"))
+    result = subprocess.run(
+        [*cli, "--no-color", *args], capture_output=True, text=True, timeout=300
+    )
+    if result.returncode:
+        raise RuntimeError(
+            f"{args[0]} failed with exit {result.returncode}; run the command to inspect the error"
+        )
+    return json.loads(result.stdout) if result.stdout.strip() else {}
+
+
+def check_group(group: str) -> None:
+    """Check real post/comment reads, saved exports, and an optional date window."""
+    result = call("scrape", group, "--limit", "3", "--no-input")
+    posts = result["posts"]
+    assert posts and len(posts) <= 3, "No group posts or post limit exceeded"
+    assert len({post["id"] for post in posts}) == len(posts), "Duplicate posts"
+    comments = []
+    for post in posts:
+        pending = list(post["comments"])
+        seen = set()
+        while pending:
+            comment = pending.pop()
+            assert comment["id"] not in seen, "Duplicate comment or reply"
+            assert comment["content"], "Empty comment"
+            assert comment["content"] != post["content"], (
+                "Post text appears as a comment"
+            )
+            seen.add(comment["id"])
+            comments.append(comment)
+            pending.extend(comment["replies"])
+    assert comments, "Use an active group with visible comments for this check"
+    assert any(c["replies"] for c in comments), "Use a group with visible reply threads"
+    assert any(c["author"]["name"] != "Unknown" for c in comments), "No comment authors"
+
+    with tempfile.TemporaryDirectory(prefix="forage-live-") as directory:
+        root = Path(directory)
+        source = root / "posts.json"
+        source.write_text(json.dumps(result), encoding="utf-8")
+        call("export", str(source), "--format", "csv", "-o", str(root / "posts.csv"))
+        with (root / "posts.csv").open() as handle:
+            assert len(list(csv.DictReader(handle))) == len(posts), "CSV loses posts"
+        with (root / "posts.comments.csv").open() as handle:
+            assert len(list(csv.DictReader(handle))) == len(comments), (
+                "CSV loses comments"
+            )
+        call("export", str(source), "--format", "sqlite", "-o", str(root / "posts.db"))
+        with sqlite3.connect(root / "posts.db") as db:
+            assert db.execute("SELECT COUNT(*) FROM posts").fetchone()[0] == len(posts)
+            assert db.execute("SELECT COUNT(*) FROM comments").fetchone()[0] == len(
+                comments
+            )
+    print(
+        "PASS live group posts, comments, replies, and CSV/SQLite exports", flush=True
+    )
+
+    until = os.environ.get("FORAGE_E2E_UNTIL")
+    if until:
+        end = date.fromisoformat(until)
+        start = end - timedelta(days=7)
+        history = call(
+            "scrape",
+            group,
+            "--limit",
+            "1",
+            "--skip-comments",
+            "--no-input",
+            "--since",
+            start.isoformat(),
+            "--until",
+            until,
+        )
+        assert history["posts"], "No historical record; use a window with known posts"
+        for post in history["posts"]:
+            assert post["timestamp"], "Historical check needs a known timestamp"
+            assert start <= datetime.fromisoformat(post["timestamp"]).date() <= end
+        print("PASS live historical date window", flush=True)
+
+
+def check_marketplace(session_path: str) -> None:
+    """Check each sort through the CLI and Facebook's selected UI control."""
+    with sync_playwright() as playwright:
+        browser = playwright.chromium.launch()
+        page = browser.new_context(storage_state=session_path).new_page()
+        try:
+            for order, label in SORT_LABELS.items():
+                result = call(
+                    "marketplace",
+                    "computer",
+                    "--limit",
+                    "1",
+                    "--max-candidates",
+                    "10",
+                    "--sort-by",
+                    order,
+                )
+                assert len(result["listings"]) == 1, "No accepted Marketplace listing"
+                assert result["listings"][0]["id"], "Missing listing ID"
+                assert result["diagnostics"]["candidates_seen"] <= 10, (
+                    "Candidate limit exceeded"
+                )
+                page.goto(result["search_url"], wait_until="domcontentloaded")
+                page.wait_for_selector('a[href*="/marketplace/item/"]')
+                radio = page.get_by_role("radio", name=label, exact=True)
+                if not radio.count():
+                    page.get_by_role("button", name=re.compile(r"^Sort by")).click()
+                assert radio.get_attribute("aria-checked") == "true", (
+                    f"Facebook ignores {order}"
+                )
+                print(f"PASS live Marketplace {order}", flush=True)
+        finally:
+            browser.close()
+
+
+def main() -> None:
+    """Verify the local setup, then read the selected live Facebook surface."""
+    doctor = call("doctor")
+    if not doctor.get("browser_installed") or not doctor.get("session_exists"):
+        raise RuntimeError(
+            "Install Chromium and save a Facebook session before live tests"
+        )
+    group = os.environ.get("FORAGE_E2E_GROUP")
+    if group:
+        check_group(group)
+    else:
+        check_marketplace(doctor["session_path"])
+
+
+if __name__ == "__main__":
+    try:
+        main()
+    except Exception as error:
+        print(f"FAIL {type(error).__name__}: {error}", file=sys.stderr)
+        sys.exit(1)

{foragefacebook-2.1.0 → foragefacebook-2.3.0}/src/forage/__init__.py

@@ -1,3 +1,3 @@
 """Forage: CLI tool to scrape private Facebook groups."""
 
-__version__ = "2.1.0"
+__version__ = "2.3.0"