• User has a direction → Conduct in-depth ranking scanning for that direction
• User has no direction → Conduct overall ranking overview + identify trends
• User wants cross-platform comparison → Conduct platform comparative analysis

/browser-cdp

1. Select the platform script; run

   scripts/qidian-rank-scraper.js

   directly for Qidian, start browser-cdp as needed for FanQie/Qimao/Jinjiang, etc.
2. Wait for list elements or SSR data to load, extract fields one by one (ranking, title, author, genre, word count, recommendations/reading count, etc.), and judge page turning (Qidian usually has 50-100 items per page, FanQie has a cap of ≈20 per page by genre)
3. When supplementary data is needed (tags, synopsis, latest update), extract from the detail page
4. Write to a Markdown file in standard format
5. For multiple rankings/genres, collect and save in groups

node scripts/qidian-rank-scraper.js --type {ranking} --outdir {output directory}

--mode auto

https://m.qidian.com

/rank/{channel}_{type}_{cat_id}

scripts/fanqie-rank-scraper.js

node scripts/fanqie-rank-scraper.js --channel 1 --type 2 --outdir {output directory}   # Male Channel Reading Rank
node scripts/fanqie-rank-scraper.js --channel all --top 15 --outdir {output directory}   # Both Male and Female Channels, Top 15 works per genre

Mandatory Check After FanQie Collection: Check the file header

Data Quality

, see references/scan-output-format.md for exception troubleshooting steps.

--period day|month|all

day

--period

scripts/jjwxc-rank-scraper.js

onebook.php

node scripts/jjwxc-rank-scraper.js --type 12 --outdir {output directory}        # List + Detail (default top 10 per channel, detail limit 100)
node scripts/jjwxc-rank-scraper.js --type 12 --top 15 --detail-limit 60  # Adjust number of works per channel/total detail works
node scripts/jjwxc-rank-scraper.js --type 12 --list-only                 # Collect only list (fast, no core metrics)

Mandatory Requirement for Jinjiang: Must have core metrics from detail pages (collection count/nutrient solution/points/word count), the script supplements this by default; see references/scan-output-format.md for collection key points.

{Platform}{Ranking Name}_{YYYYMMDD}.md

QidianNewSignedNovelsRank_20260425.md

[Sparse Data] Actually collected N entries

[Missing Field: {Field Name}]

[Parsing Exception]

--

[To be Supplemented]

• For synopses exceeding 100 words after cleaning, truncate at the nearest period/question mark/exclamation mark and add

  ...

• Platform template text is not counted towards the 100-word limit (delete template first, then truncate)

- Data Quality: [OK / Issues Exist]
- Valid Entries: {N} / {Total}
- Issue Summary: {None / Specific Issue Description}

• User provides path to existing scanning result file → Directly load into "Data Analysis"
• User provides link → Fetch using WebFetch
• User pastes/screenshots → Manually parse and enter analysis

• Load

  references/genre-trends.md

• Clearly mark: "The following analysis is based on historical trend data; it can only be used as a candidate hypothesis until real-time ranking verification is completed." And list the rankings that need to be rescanned.

Mandatory Collection Requirement: If

--list-only

is used or the file header is marked

[List Only - No Core Metrics]

, the data is insufficient to support the following analysis dimensions and is deemed unqualified.

1. Genre Distribution: Which genres are most prevalent on the current rankings
2. New Genre Signals: Recently emerging genre types
3. Classic Genre Changes: Trends of established genres (rising/stable/declining)
4. Word Count and Updates: Word count range and update frequency of ranked works
5. Title Patterns: Naming rules of ranked works
6. Opening Selling Points: Repeated keywords in synopses/tags
7. New Element Comparison: Compare with previous/ similar rankings, mark newly emerged character settings, opening entry points, and plot tropes

• Scan Time: {Date}
• Core Findings: {One-sentence Summary}

• {Emerging or rising genre, with basis}

• {Current status of established genres, with basis}

• {Pattern description + representative work}

• {Entry point description + representative work}

• {Trope description + representative work}

• Word Count Range: Ranked works are concentrated in {X}-{Y} thousand words
• Update Frequency: {X} words per day is the mainstream
• Title Characteristics: {Naming pattern summary}
• Tag Hot Words: {High-frequency tag words}

1. {Direction + Why it's worth focusing on + Feasibility assessment}
2. {Direction + Why it's worth focusing on + Feasibility assessment}
3. {Direction + Why it's worth focusing on + Feasibility assessment}

Topic Decision.md

topic-decision.md

{outdir}/Topic Decision.md

• Feasibility Upper Limit: If the ranking is marked

  [Sparse Data]

  or there are <15 samples in the same direction (<10 for small platforms) ⇒ Do not mark "High", force it to "Medium" + note to verify first; built-in knowledge mode is always marked "Medium".
• Do not output genres that cannot be supported by project materials; do not only look at popularity, must provide feasibility and failure risks; do not ignore platform tone differences (Qidian male channel and Jinjiang female channel have completely different aesthetics).

• Respond in the user's language; use the same language as the user
• Follow Chinese Copywriting Guidelines for Chinese responses