feat: 增加章节学习次数功能#616
Open
macarons-me wants to merge 3 commits into
Open
Conversation
fix: 优化章节学习次数访问表现 feat: 添加章节学习次数配置说明及失败处理逻辑 fix: 恢复意外的修改
|
No actionable comments were generated in the recent review. 🎉 ℹ️ Recent review info⚙️ Run configurationConfiguration used: defaults Review profile: CHILL Plan: Pro Run ID: 📒 Files selected for processing (1)
🚧 Files skipped from review as they are similar to previous changes (1)
📝 WalkthroughWalkthroughAdds an optional post-study phase that, when enabled, iterates courses after normal task completion, fetches chapter data, runs ChangesChapter Learning Count Increase
Estimated code review effort🎯 3 (Moderate) | ⏱️ ~25 minutes Suggested reviewers
Poem
🚥 Pre-merge checks | ✅ 5✅ Passed checks (5 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing Touches🧪 Generate unit tests (beta)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 2
🧹 Nitpick comments (2)
main.py (1)
552-559: 📐 Maintainability & Code Quality | 🔵 Trivial | 💤 Low valueHoist
target_countassignment out of the loop.
common_config["target_count"] = target_countis invariant across iterations and only needs to be set once before the loop. Minor cleanup.♻️ Proposed tidy-up
if add_learning_count: logger.info("刷课完成，开始增加章节学习次数...") + common_config["target_count"] = target_count for course in course_task: - common_config["target_count"] = target_count increase_learning_count_for_course(chaoxing, course, common_config)🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the rest with a brief reason, keep changes minimal, and validate. In `@main.py` around lines 552 - 559, Hoist the invariant target_count assignment out of the course loop in the post-processing block in main.py. Move common_config["target_count"] = target_count to just before the for course in course_task loop, and keep increase_learning_count_for_course and the completion logging unchanged so each iteration reuses the same config value without redundant reassignment.api/base.py (1)
1214-1215: 🚀 Performance & Scalability | 🔵 TrivialHeads-up: runtime scales linearly with
target_countat ~30s each.Each chapter visit blocks for a hard-coded
time.sleep(30), so with the defaulttarget_count=100a single course takes ~50 minutes (plus per-request overhead), repeated for every course. Consider making the interval configurable or documenting the expected duration so users aren't surprised.🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the rest with a brief reason, keep changes minimal, and validate. In `@api/base.py` around lines 1214 - 1215, The chapter-visit loop in the relevant course-processing flow uses a hard-coded 30-second sleep, which makes runtime scale linearly with target_count and can surprise users. Update the logic around the time.sleep(30) step to use a configurable interval or expose it as a parameter in the surrounding function, and make sure the default behavior is clearly documented in the method handling chapter traversal.
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In `@api/base.py`:
- Around line 1122-1134: The GET request in the student study Ajax call is
missing a timeout, so it can hang indefinitely if the connection stalls. Update
the _session.get call inside the relevant request path to pass a timeout value
consistent with _send_monitor_heartbeat and _extract_and_send_setlog (use the
same 5-second timeout) so the request fails fast like the other network calls.
- Around line 1190-1193: The loop in the reusable point-replication logic can
spin forever when points is empty, because the outer while in the method that
processes points never makes progress. Update the method containing the
while/for iteration to fail safe on an empty points input before entering the
loop, so total cannot stay stuck at 0; keep the fix localized to that helper
rather than relying on increase_learning_count_for_course to guard it.
---
Nitpick comments:
In `@api/base.py`:
- Around line 1214-1215: The chapter-visit loop in the relevant
course-processing flow uses a hard-coded 30-second sleep, which makes runtime
scale linearly with target_count and can surprise users. Update the logic around
the time.sleep(30) step to use a configurable interval or expose it as a
parameter in the surrounding function, and make sure the default behavior is
clearly documented in the method handling chapter traversal.
In `@main.py`:
- Around line 552-559: Hoist the invariant target_count assignment out of the
course loop in the post-processing block in main.py. Move
common_config["target_count"] = target_count to just before the for course in
course_task loop, and keep increase_learning_count_for_course and the completion
logging unchanged so each iteration reuses the same config value without
redundant reassignment.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: defaults
Review profile: CHILL
Plan: Pro
Run ID: b4c6f582-40e7-4d91-9850-d4bda6ed49e0
📒 Files selected for processing (5)
README.mdapi/base.pyapi/process.pyconfig_template.inimain.py
There was a problem hiding this comment.
Caution
Some comments are outside the diff and can’t be posted inline due to platform limitations.
⚠️ Outside diff range comments (2)
api/base.py (2)
1125-1138: 🩺 Stability & Availability | 🟠 Major | ⚡ Quick winKeep transient request errors inside the failure counter.
A timeout/connection error from this GET bypasses
consecutive_failuresand aborts the whole count phase. CatchRequestExceptionhere and returnNone, matching the non-200 path.🛡️ Proposed fix
- _resp = _session.get( - url="https://mooc1.chaoxing.com/mooc-ans/mycourse/studentstudyAjax", - params={ - "courseId": _course["courseId"], - "clazzid": _course["clazzId"], - "chapterId": point["id"], - "cpi": _course["cpi"], - "verificationcode": "", - "mooc2": 1, - "microTopicId": 0, - "editorPreview": 0, - }, - timeout=8, - ) + try: + _resp = _session.get( + url="https://mooc1.chaoxing.com/mooc-ans/mycourse/studentstudyAjax", + params={ + "courseId": _course["courseId"], + "clazzid": _course["clazzId"], + "chapterId": point["id"], + "cpi": _course["cpi"], + "verificationcode": "", + "mooc2": 1, + "microTopicId": 0, + "editorPreview": 0, + }, + timeout=8, + ) + except RequestException as exc: + logger.error(f"章节访问失败 -> [{point['title']}]: {exc}") + return None🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the rest with a brief reason, keep changes minimal, and validate. In `@api/base.py` around lines 1125 - 1138, The GET in the course study flow bypasses the failure counter when it raises a transient request error instead of returning a non-200 response. Update the request handling around _session.get in the student study fetch path to catch RequestException, treat it like the existing non-200 branch, and return None so the caller’s consecutive_failures logic continues to count the failure. Preserve the current behavior for successful responses and keep the change localized to the method that performs the study-page fetch.
1146-1168: 🗄️ Data Integrity & Integration | 🟠 Major | ⚡ Quick winOnly increment
totalaftersetlogsucceeds.
_extract_and_send_setlog()currently has no success signal, so missingsetlog, HTTP failures, and exceptions still lead tototal += 1. Since this is the count-recording API, treat failure as a failed visit.🛡️ Proposed fix
- def _extract_and_send_setlog(self, html_text): + def _extract_and_send_setlog(self, html_text) -> bool: @@ if not match: logger.trace("未在响应中找到 setlog URL") - return + return False setlog_url = match.group(1) try: session = SessionManager.get_session() resp = session.get(setlog_url, timeout=5) logger.trace(f"Setlog sent -> {resp.status_code}") - except Exception as e: + return resp.ok + except RequestException as e: logger.trace(f"Setlog failed (non-critical): {e}") + return False @@ # 第 1 步：从 HTML 中提取 setlog URL 并执行（真正的计次 API） - self._extract_and_send_setlog(html_text) + if not self._extract_and_send_setlog(html_text): + logger.error(f"章节 setlog 发送失败, 当前章节: {point['title']}") + consecutive_failures += 1 + if consecutive_failures >= max_consecutive_failures: + logger.error( + f"章节学习次数增加连续失败 {consecutive_failures} 次, 终止任务" + ) + return StudyResult.ERROR + continue + + consecutive_failures = 0 # 第 2 步：立即发送 monitor 心跳包（模拟 fn()） self._send_monitor_heartbeat(course, point)Also applies to: 1215-1228
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the rest with a brief reason, keep changes minimal, and validate. In `@api/base.py` around lines 1146 - 1168, The _extract_and_send_setlog helper currently logs failures but does not tell callers whether the setlog call actually succeeded, so total can be incremented even when the visit record was not sent. Change _extract_and_send_setlog to return a success/failure signal based on finding the setlog URL, the session.get call, and the HTTP response, and then update the callers around total += 1 to only increment when _extract_and_send_setlog reports success. Keep the logic aligned with the existing SessionManager.get_session and logger.trace flow.
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Outside diff comments:
In `@api/base.py`:
- Around line 1125-1138: The GET in the course study flow bypasses the failure
counter when it raises a transient request error instead of returning a non-200
response. Update the request handling around _session.get in the student study
fetch path to catch RequestException, treat it like the existing non-200 branch,
and return None so the caller’s consecutive_failures logic continues to count
the failure. Preserve the current behavior for successful responses and keep the
change localized to the method that performs the study-page fetch.
- Around line 1146-1168: The _extract_and_send_setlog helper currently logs
failures but does not tell callers whether the setlog call actually succeeded,
so total can be incremented even when the visit record was not sent. Change
_extract_and_send_setlog to return a success/failure signal based on finding the
setlog URL, the session.get call, and the HTTP response, and then update the
callers around total += 1 to only increment when _extract_and_send_setlog
reports success. Keep the logic aligned with the existing
SessionManager.get_session and logger.trace flow.
ℹ️ Review info
⚙️ Run configuration
Configuration used: defaults
Review profile: CHILL
Plan: Pro
Run ID: 26917f4c-7839-4388-9c48-340fd4480c1d
📒 Files selected for processing (3)
api/base.pyapi/process.pymain.py
🚧 Files skipped from review as they are similar to previous changes (2)
- api/process.py
- main.py
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
问题
在学习时发现部分课程有章节学习次数的考核目标，比较变态
解决
通过分析章节页面的网络行为，并结合其他同学对该考核目标的反馈，成功推测并模拟了前端的关键请求行为，从而实现了该自动化功能
Summary by CodeRabbit
add_learning_countandtarget_countsettings (with matching CLI options) to control whether the extra step runs and the total target count.