langgenius/dify
1
0
Fork 0
mirror of https://github.com/langgenius/dify.git synced 2026-07-22 04:25:29 -04:00
Code Issues 775 Packages Projects Releases 10 Wiki Activity

I'm using the webscraper component in my workflow, but it gives me an error. #6533

New Issue
Closed
opened 2026-02-21 18:16:10 -05:00 by yindo · 2 comments
yindo commented 2026-02-21 18:16:10 -05:00
Owner
Copy Link
Copy Source

Originally created by @starweavingdream on GitHub (Nov 4, 2024).

Self Checks

  • This is only for bug report, if you would like to ask a question, please head to Discussions.
  • I have searched for existing issues search for existing issues, including closed ones.
  • I confirm that I am using English to submit this report (我已阅读并同意 Language Policy).
  • [FOR CHINESE USERS] 请务必使用英文提交 Issue，否则会被关闭。谢谢！:）
  • Please do not modify this template :) and fill in all the required fields.

Dify version

0.10.1

Cloud or Self Hosted

Self Hosted (Docker)

Steps to reproduce

I'm using the webscraper component in my workflow, but it gives me an error.The error message is as follows:
Run failed: Failed to invoke tool: 'gbk' codec can't encode character '\u30fb' in position 35658: illegal multibyte sequence.

✔️ Expected Behavior

No response

❌ Actual Behavior

No response

Originally created by @starweavingdream on GitHub (Nov 4, 2024). ### Self Checks - [X] This is only for bug report, if you would like to ask a question, please head to [Discussions](https://github.com/langgenius/dify/discussions/categories/general). - [X] I have searched for existing issues [search for existing issues](https://github.com/langgenius/dify/issues), including closed ones. - [X] I confirm that I am using English to submit this report (我已阅读并同意 [Language Policy](https://github.com/langgenius/dify/issues/1542)). - [X] [FOR CHINESE USERS] 请务必使用英文提交 Issue，否则会被关闭。谢谢！:） - [X] Please do not modify this template :) and fill in all the required fields. ### Dify version 0.10.1 ### Cloud or Self Hosted Self Hosted (Docker) ### Steps to reproduce I'm using the `webscraper` component in my workflow, but it gives me an error.The error message is as follows: Run failed: Failed to invoke tool: 'gbk' codec can't encode character '\u30fb' in position 35658: illegal multibyte sequence. ### ✔️ Expected Behavior _No response_ ### ❌ Actual Behavior _No response_
yindo added the 🐞 bug label 2026-02-21 18:16:10 -05:00
yindo closed this issue 2026-02-21 18:16:10 -05:00
yindo commented 2026-02-21 18:16:10 -05:00
Author
Owner
Copy Link
Copy Source

@dosubot[bot] commented on GitHub (Nov 4, 2024):

The error you're encountering with the webscraper component is related to character encoding, specifically with the 'gbk' codec, which is unable to encode a particular character ('\u30fb'). This issue typically arises when the content being processed contains characters that are not supported by the specified encoding.

To address this issue, you can try the following steps:

  1. Check Encoding Settings: Ensure that the webscraper is set to use an encoding that supports the characters in your content. UTF-8 is a common choice as it supports a wide range of characters.

  2. Modify Encoding Handling: If possible, modify the webscraper component to handle encoding more flexibly. The component uses the chardet library to detect encoding, but you might need to override this if it's not detecting correctly. You can manually set the encoding to UTF-8 or another suitable encoding.

  3. Update Content Handling: If you have access to the code, you can update the content handling part to ensure it decodes using a more appropriate encoding. Here's a snippet that shows how encoding is typically handled:

    # Detect encoding using chardet
detected_encoding = chardet.detect(response.content)
encoding = detected_encoding["encoding"]
if encoding:
    try:
        content = response.content.decode(encoding)
    except (UnicodeDecodeError, TypeError):
        content = response.text
else:
    content = response.text

    You might want to ensure that the fallback (response.text) uses UTF-8.

  4. Error Handling: Implement additional error handling to catch and manage encoding errors gracefully, possibly by logging them for further analysis.

These steps should help mitigate the encoding issue you're facing with the webscraper component.

To continue talking to Dosu, mention @dosu.

@dosubot[bot] commented on GitHub (Nov 4, 2024): <!-- Answer --> The error you're encountering with the `webscraper` component is related to character encoding, specifically with the 'gbk' codec, which is unable to encode a particular character ('\u30fb'). This issue typically arises when the content being processed contains characters that are not supported by the specified encoding. To address this issue, you can try the following steps: 1. **Check Encoding Settings**: Ensure that the `webscraper` is set to use an encoding that supports the characters in your content. UTF-8 is a common choice as it supports a wide range of characters. 2. **Modify Encoding Handling**: If possible, modify the `webscraper` component to handle encoding more flexibly. The component uses the `chardet` library to detect encoding, but you might need to override this if it's not detecting correctly. You can manually set the encoding to UTF-8 or another suitable encoding. 3. **Update Content Handling**: If you have access to the code, you can update the content handling part to ensure it decodes using a more appropriate encoding. Here's a snippet that shows how encoding is typically handled: ```python # Detect encoding using chardet detected_encoding = chardet.detect(response.content) encoding = detected_encoding["encoding"] if encoding: try: content = response.content.decode(encoding) except (UnicodeDecodeError, TypeError): content = response.text else: content = response.text ``` You might want to ensure that the fallback (`response.text`) uses UTF-8. 4. **Error Handling**: Implement additional error handling to catch and manage encoding errors gracefully, possibly by logging them for further analysis. These steps should help mitigate the encoding issue you're facing with the `webscraper` component. <!-- Dosu Comment Footer --> *To continue talking to [Dosu](https://dosu.dev), mention @dosu.*
yindo commented 2026-02-21 18:16:11 -05:00
Author
Owner
Copy Link
Copy Source

@crazywoola commented on GitHub (Nov 4, 2024):

Try using Jina.ai instead. If you want to resolve this issue, you may need to modify the code to recognize the GBK character encoding. Our webscraper is a lightweight solution which might not support all encodings. StackOverflow

@crazywoola commented on GitHub (Nov 4, 2024): Try using Jina.ai instead. If you want to resolve this issue, you may need to modify the code to recognize the GBK character encoding. Our `webscraper` is a lightweight solution which might not support all encodings. [StackOverflow](https://stackoverflow.com/questions/3218014/unicodeencodeerror-gbk-codec-cant-encode-character-illegal-multibyte-sequen)
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
Knowledge Pipeline
Proposal
WIP
cloud
dependencies
feat:webapp
good first issue
outdated
performance
pull-request
Mirrored from GitHub Pull Request
 python:uv
refactor
size:L
stale
status: accepting prs
status: blocked
status: in discussion
stt & tts
vulnerablity
web
wont-fix
🌊 feat:workflow
🌚 invalid
🐞 bug
👻 feat:rag
💪 enhancement
📚 documentation
🔨 feat:tools
🙋‍♂️ question
🙏 help wanted
🤔 cant-reproduce
🤖 feat:agent
No Label 🐞 bug
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
yindo
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: langgenius/dify#6533
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?