cultural-tourism-bilibili-feed

Bilibili cultural tourism video content source (Dubaoya)

This duck helps you scan Bilibili for viral cultural tourism videos by keyword—fishing out the hottest travel Vlogs, city documentaries, and in-depth scenic area videos, laying them out in a clickable viral video table in the terminal, then clustering them into several cultural tourism topic directions to build a directly actionable long-video benchmarking list.

Bilibili is the high ground for in-depth cultural tourism videos: travel Vlogs, city documentaries, and culture-oriented topics all produce long-tail viral hits here. Suitable forcultural tourism bureaus, scenic area operations, city cultural tourism accounts, travel UP creatorsto find long-video topics, see benchmarks in the same track, and carve out narrative angles.

Data goes through doubaoya.com as a single line, authentication uses your own token (environment variable DOUBAOYA_API_KEY, in the form dyh_…）。

Note: the underlying layer is the Bilibili content feed, which fetches videos by the keyword you give. "Cultural tourism" is using keywords to treat it as a cultural tourism topic lens—results depend on the feed's hits for your word; the closer the word is to cultural tourism, the more accurate it is.

---

Use cases

Scenario	How to use	What you get
Long-video topic selection	Use 文旅、旅行 Vlog to scan high-play viral hits	See clearly what is hot in cultural tourism long videos right now
City documentary benchmarking	Use 城市、城市漫游 etc.	Lock onto the narrative and structure of city documentaries
In-depth scenic area orientation	Use 景区、古建、国风 to find angles	Find how in-depth scenic area videos are shot
Viral video benchmarking	See which angles high-like videos cluster around	Find content angles in the same track worth benchmarking
Narrative angle breakdown	Look at the titles and structure of high-like videos	Distill the viral formulas of cultural tourism long videos

---

Workflow (4 steps)

1. Set the keyword

Extract one cultural tourism direction keyword(required) from the user's description, such as 文旅、旅行 Vlog、城市漫游、景区、古建、国风. Broad words get more hits, narrow words are more focused; scan only one keyword at a time.

2. Call the script

python3 "$SKILL_PATH/scripts/fetch_culture_feed.py" "旅行 Vlog"

Pagination / adjust items per page (optional):

python3 "$SKILL_PATH/scripts/fetch_culture_feed.py" "城市漫游" --page 2 --size 30

The script prints the data from the success envelope as JSON to stdout.Run the script only once per query, read the full stdout directly, do not use head/tail to preview, and do not call repeatedly with the same parameters.

3. Render the viral video table

From data.items(video array), take the fields and lay them out as a Markdown table. The core fields this interface reliably returns are title(title) and likeCount(likes); read defensively—fields may be missing, leave them blank if so, do not error, and do not invent links or UP creators the interface did not return. If a given return happens to include a link, then render the title as a clickable link; otherwise plain text is fine.

Title	Likes
Example cultural tourism video	5.6w

4. Cluster into topic directions + one-sentence insight

Take this batch of videos from a cultural tourism anglecluster(e.g. travel Vlog / city documentary / scenic area deep dive / ancient architecture guofeng / food exploration), pick out representative viral hits for each direction, and form a short benchmarking list. At the end, add one line in this duck's tonetopic insight: which angle is hottest in current cultural tourism long-form video, and which narrative still has room. Don't pile on clichés, don't ask the user their purpose.

---

Get key (passcode)

1. Open doubaoya.com
2. Log in
3. Go to passcode center
4. Generate passcode(in the form dyh_…）

Configure to environment variable (the script only recognizes this):

export DOUBAOYA_API_KEY="dyh_你的口令"

Iron rule: the passcode is never printed, never written to a file, never echoed back to the user. The script itself also never outputs the passcode. All requests are sent only to doubaoya.com。

---

Interface and envelope

• POST https://doubaoya.com/api/apis/bilibili/bilibili-playlet-feed/call
• Auth header:Authorization: Bearer $DOUBAOYA_API_KEY
• Request body:{ "keyword": "旅行 Vlog", "pageNum": 1, "pageSize": 20 }
  • keyword: string, required
  • pageNum: integer, optional (default 1, controlled by --page controlled)
  • pageSize: integer, optional (default 20, controlled by --size controlled)
• Return envelope:

  {
    "success": true,
    "requestId": "...",
    "data": { "items": [ { "title": "...", "likeCount": 56000 } ] },
    "error": null
  }
  

• First check success: is true only then read data; otherwise read error.code / error.message。

---

Error handling

When the script fails, print to stderr [error] CODE: message and exit with code 1. Common cases:

HTTP	code	Meaning	Handling
401	MISSING_API_KEY / UNAUTHORIZED	No passcode or invalid passcode	Check DOUBAOYA_API_KEY, go to the passcode center to regenerate
400	VALIDATION_ERROR	Invalid parameter (e.g. keyword is empty)	Fix the keyword and retry
402	INSUFFICIENT_CREDITS	Insufficient quota	Go to doubaoya.com to top up/renew quota
502	PROVIDER_FAILED	Temporary upstream failure (automatically refunded）	safe to retry

502 PROVIDER_FAILED will automatically refund, retrying is safe and will not double-charge.

---

Directory structure

cultural-tourism-bilibili-feed/
├── SKILL.md                    # 本文件
└── scripts/
    └── fetch_culture_feed.py   # 零依赖脚本（urllib），调用 doubaoya.com