Upload 5 files

LICENSE

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

README.md

@@ -1,170 +1,74 @@
----
-license: openrail++
-tags:
-- art
-- stable diffusion
-- ControlNet
-- SDXL
-- Diffusion-XL
-pipeline_tag: text-to-image
----
-# MistoLine
-## Control Every Line!
-
-![Intro Image](assets/intro.png)  
-[GitHub Repo](https://github.com/TheMistoAI/MistoLine)
-
-## NEWS!!!!! Anyline-preprocessor is released!!!!
-[Anyline Repo](https://github.com/TheMistoAI/ComfyUI-Anyline)
-
-**MistoLine: A Versatile and Robust SDXL-ControlNet Model for Adaptable Line Art Conditioning.**  
-
-MistoLine is an SDXL-ControlNet model that can adapt to any type of line art input, demonstrating high accuracy and excellent stability. It can generate  high-quality images (with a short side greater than 1024px) based on user-provided line art of various types, including hand-drawn sketches, different  ControlNet line preprocessors, and model-generated outlines. MistoLine eliminates the need to select different ControlNet models for different line  preprocessors, as it exhibits strong generalization capabilities across diverse line art conditions.  
-
-We developed MistoLine by employing a novel line preprocessing algorithm **[Anyline](https://github.com/TheMistoAI/ComfyUI-Anyline)** and retraining the ControlNet model based on the Unet of stabilityai/  stable-diffusion-xl-base-1.0, along with innovations in large model training engineering. MistoLine showcases superior performance across
-different types of line art inputs, surpassing existing ControlNet models in terms of detail restoration, prompt alignment, and stability, particularly in more complex  scenarios.  
-
-MistoLine maintains consistency with the ControlNet architecture released by @lllyasviel, as illustrated in the following schematic diagram:  
-![ControlNet architecture](assets/controlnet_1.png)  
-![ControlNet architecture](assets/controlnet_2.png)  
-*reference：https://github.com/lllyasviel/ControlNet*  
-
-More information about ControlNet can be found in the following references:  
-https://github.com/lllyasviel/ControlNet  
-https://huggingface.co/docs/diffusers/main/en/api/pipelines/controlnet_sdxl  
-
-The model is compatible with most SDXL models, except for PlaygroundV2.5, CosXL, and SDXL-Lightning(maybe). It can be used in conjunction with LCM and other ControlNet models.  
-
-The following usage of this model is not allowed:  
-* Violating laws and regulations
-* Harming or exploiting minors
-* Creating and spreading false information
-* Infringing on others' privacy
-* Defaming or harassing others
-* Automated decision-making that harms others' legal rights
-* Discrimination based on social behavior or personal characteristics
-* Exploiting the vulnerabilities of specific groups to mislead their behavior
-* Discrimination based on legally protected characteristics
-* Providing medical advice and diagnostic results
-* Improperly generating and using information for purposes such as law enforcement and immigration
-
-If you use or distribute this model for commercial purposes, you must comply with the following conditions:  
-1. Clearly acknowledge the contribution of TheMisto.ai to this model in the documentation, website, or other prominent and visible locations of your product.
-   Example: "This product uses the MistoLine-SDXL-ControlNet developed by TheMisto.ai."
-2. If your product includes about screens, readme files, or other similar display areas, you must include the above attribution information in those areas.
-3. If your product does not have the aforementioned areas, you must include the attribution information in other reasonable locations within the product to ensure that end-users can notice it.
-4. You must not imply in any way that TheMisto.ai endorses or promotes your product. The use of the attribution information is solely to indicate the origin of this model.  
-If you have any questions about how to provide attribution in specific cases, please contact info@themisto.ai.  
-
-署名条款  
-如果您在商业用途中使用或分发本模型,您必须满足以下条件:  
-1. 在产品的文档,网站,或其他主要可见位置,明确提及 TheMisto.ai 对本软件的贡献。
-   示例: "本产品使用了 TheMisto.ai 开发的 MistoLine-SDXL-ControlNet。"
-2. 如果您的产品包含有关屏幕,说明文件,或其他类似的显示区域,您必须在这些区域中包含上述署名信息。
-3. 如果您的产品没有上述区域,您必须在产品的其他合理位置包含署名信息,以确保最终用户能够注意到。
-4. 您不得以任何方式暗示 TheMisto.ai 为您的产品背书或促销。署名信息的使用仅用于表明本模型的来源。  
-如果您对如何在特定情况下提供署名有任何疑问,请联系info@themisto.ai。
-
-The model output is not censored and the authors do not endorse the opinions in the generated content. Use at your own risk.
-
-## Apply with Different Line Preprocessors
-![preprocessors](assets/preprocessors.png)  
-
-## Compere with Other Controlnets
-![comparison](assets/comparison.png)  
-
-## Application Examples
-
-### Sketch Rendering
-*The following case only utilized MistoLine as the controlnet：*
-![Sketch Rendering](assets/sketch_rendering.png)  
-
-### Model Rendering
-*The following case only utilized Anyline as the preprocessor and MistoLine as the controlnet.*
-![Model Rendering](assets/model_rendering.png)
-
-## ComfyUI Recommended Parameters
-```
-sampler steps:30
-CFG:7.0
-sampler_name:dpmpp_2m_sde
-scheduler:karras
-denoise:0.93
-controlnet_strength:1.0
-stargt_percent:0.0
-end_percent:0.9
-```
-## Diffusers pipeline
-Make sure to first install the libraries:
-```
-pip install accelerate transformers safetensors opencv-python diffusers
-```
-And then we're ready to go:
-```
-from diffusers import ControlNetModel, StableDiffusionXLControlNetPipeline, AutoencoderKL
-from diffusers.utils import load_image
-from PIL import Image
-import torch
-import numpy as np
-import cv2
-
-prompt = "aerial view, a futuristic research complex in a bright foggy jungle, hard lighting"
-negative_prompt = 'low quality, bad quality, sketches'
-
-image = load_image("https://huggingface.co/datasets/hf-internal-testing/diffusers-images/resolve/main/sd_controlnet/hf-logo.png")
-
-controlnet_conditioning_scale = 0.5
-
-controlnet = ControlNetModel.from_pretrained(
-    "TheMistoAI/MistoLine",
-    torch_dtype=torch.float16,
-    variant="fp16",
-)
-vae = AutoencoderKL.from_pretrained("madebyollin/sdxl-vae-fp16-fix", torch_dtype=torch.float16)
-pipe = StableDiffusionXLControlNetPipeline.from_pretrained(
-    "stabilityai/stable-diffusion-xl-base-1.0",
-    controlnet=controlnet,
-    vae=vae,
-    torch_dtype=torch.float16,
-)
-pipe.enable_model_cpu_offload()
-
-image = np.array(image)
-image = cv2.Canny(image, 100, 200)
-image = image[:, :, None]
-image = np.concatenate([image, image, image], axis=2)
-image = Image.fromarray(image)
-
-images = pipe(
-    prompt, negative_prompt=negative_prompt, image=image, controlnet_conditioning_scale=controlnet_conditioning_scale,
-    ).images
-
-images[0].save(f"hug_lab.png")
-```
+# Discord-Scraper
 
+Pipeline to scrape prompt + image url pairs from Discord channels. The idea started by wanting to scrape the image-prompt pairs from [share-dalle-3](https://discord.com/channels/823813159592001537/1158354590463447092) Discord channel from [LAION server](https://discord.com/invite/eq3cAMZtCC). But now you can re-use the scraper to work with any channel you want.
 
-## Checkpoints
-* mistoLine_rank256.safetensors : General usage version, for ComfyUI and AUTOMATIC1111-WebUI.  
-* mistoLine_fp16.safetensors : FP16 weights, for ComfyUI and AUTOMATIC1111-WebUI.
+## How to use
 
-## !!!mistoLine_rank256.safetensors better than mistoLine_fp16.safetensors
-## !!!mistoLine_rank256.safetensors 表现更加出色！！
+Clone the repo `git clone https://github.com/LAION-AI/Discord-Scrapers.git`
 
-## ComfyUI Usage
-![ComfyUI](assets/comfyui.png)
+1. Set up a virtual environment and install the requirements with `pip install -r requirements.txt`
+2. Get your `DISCORD_TOKEN` and `HF_TOKEN` and add as environment variables. 
+   1. `DISCORD_TOKEN` can be obtained by looking at developer tools in your Web Browser
+   2. `HF_TOKEN` can be obtained by logging in to HuggingFace and looking at your profile
+3. Get the `channel_id` from the Discord channel you want to scrape. You can do this by enabling developer mode in Discord and right clicking the channel you want to scrape.
+4. Create a `condition_fn` and a `parse_fn` that will be used to filter and parse the messages. You can use the ones I created as an example.
+5. Create your scraping script and optionally your `config.json`
 
-## 中国（大陆地区）便捷下载地址： 
-链接：https://pan.baidu.com/s/1DbZWmGJ40Uzr3Iz9RNBG_w?pwd=8mzs  
-提取码：8mzs  
 
-## Citation
-```
-@misc{
-      title={Adding Conditional Control to Text-to-Image Diffusion Models}, 
-      author={Lvmin Zhang, Anyi Rao, Maneesh Agrawala},
-      year={2023},
-      eprint={2302.05543},
-      archivePrefix={arXiv},
-      primaryClass={cs.CV}
-}
+**NOTE PAY ATTENTION TO THE FUNC SIGNATURE OF parse_fn and condition_fn**
+
+```python
+import os
+from typing import Any, Dict, List
+
+from scraper import ScraperBot, ScraperBotConfig, HFDatasetScheme
+
+def parse_fn(message: Dict[str, Any]) -> List[HFDatasetScheme]:
+    ...
+
+def condition_fn(message: Dict[str, Any]) -> bool:
+    ...
+
+if __name__ == "__main__":
+    config_path = os.path.join(os.path.dirname(__file__), "config.json")
+    config = ScraperBotConfig.from_json(config_path)
+
+    bot = ScraperBot(config=config, parse_fn=parse_fn, condition_fn=condition_fn)
+    bot.scrape(fetch_all=False, push_to_hub=False)
 ```
+
+
+## Main Components
+
+### ScraperBotConfig
+
+Dataclass with configuration attributes to be used by the ScraperBot. You can create your own config.json file and load it with `ScraperBotConfig.from_json(path_to_config)`.
+
+attributes:
+- base_url: str, The base url of the Discord API (in chase it changes)
+- channel_id: str, The id of the channel you want to scrape
+- limit: int, The number of messages to fetch (from my tests the max allowed by Discord is 100)
+- hf_dataset_name: str, The name of the dataset you want to push to HuggingFace
+
+### ScraperBot
+
+Implementation of the scraper. Get's the messages from the Discord API and filters them using the `condition_fn`. Then parses the messages using the `parse_fn` and pushes the dataset to HuggingFace.
+
+attributes:
+- config: ScraperBotConfig, The configuration to be used by the bot
+- parse_fn: Callable[[Dict[str, Any]], List[HFDatasetScheme]], The function to parse the messages
+- condition_fn: Callable[[Dict[str, Any]], bool], The function to filter the messages
+
+methods:
+
+#### scrape(fetch_all: bool = False, push_to_hub: bool = False) -> Dataset 
+
+Scrapes the messages and optionally pushes the dataset to HuggingFace.
+
+args:
+- fetch_all: bool, If True will fetch all the messages from the channel. If False will fetch only the messages that weren't processed yet.
+- push_to_hub: bool, If True will push the dataset to HuggingFace. If False will only return the dataset.
+
+**NOTE: If you want to push the dataset to HuggingFace you need to set the `HF_TOKEN` environment variable.**
+**NOTE 2: If the dataset doesn't exist in HuggingFace it will be created. If it already exists it will be updated.**
+  

config.json

@@ -1,57 +1,9 @@
 {
-  "_class_name": "ControlNetModel",
-  "_diffusers_version": "0.27.2",
-  "act_fn": "silu",
-  "addition_embed_type": "text_time",
-  "addition_embed_type_num_heads": 64,
-  "addition_time_embed_dim": 256,
-  "attention_head_dim": [
-    5,
-    10,
-    20
-  ],
-  "block_out_channels": [
-    320,
-    640,
-    1280
-  ],
-  "class_embed_type": null,
-  "conditioning_channels": 3,
-  "conditioning_embedding_out_channels": [
-    16,
-    32,
-    96,
-    256
-  ],
-  "controlnet_conditioning_channel_order": "rgb",
-  "cross_attention_dim": 2048,
-  "down_block_types": [
-    "DownBlock2D",
-    "CrossAttnDownBlock2D",
-    "CrossAttnDownBlock2D"
-  ],
-  "downsample_padding": 1,
-  "encoder_hid_dim": null,
-  "encoder_hid_dim_type": null,
-  "flip_sin_to_cos": true,
-  "freq_shift": 0,
-  "global_pool_conditions": false,
-  "in_channels": 4,
-  "layers_per_block": 2,
-  "mid_block_scale_factor": 1,
-  "mid_block_type": "UNetMidBlock2DCrossAttn",
-  "norm_eps": 1e-05,
-  "norm_num_groups": 32,
-  "num_attention_heads": null,
-  "num_class_embeds": null,
-  "only_cross_attention": false,
-  "projection_class_embeddings_input_dim": 2816,
-  "resnet_time_scale_shift": "default",
-  "transformer_layers_per_block": [
-    1,
-    2,
-    10
-  ],
-  "upcast_attention": false,
-  "use_linear_projection": true
+    "base_url": "https://discord.com/api/v9",
+    "channel_id": "1159217496390389801",
+    "limit": 100,
+    "max_chunk_size": 300,
+    "embed_data": false,
+    "data_key": "image",
+    "hf_dataset_name": "laion/gpt4v-dataset"
 }

requirements.txt

@@ -0,0 +1,6 @@
+requests==2.31.0
+git+https://github.com/ZachNagengast/datasets.git@a6bd7b4a268dbda6b86d4ca59f5d2a78848b0199
+Pillow==10.0.1
+huggingface_hub>=0.18
+numpy
+fsspec==2023.9.2

scrape.py

@@ -0,0 +1,97 @@
+import io
+import os
+import re
+import pandas as pd
+from typing import Any, Dict, List
+import requests
+from PIL import Image as PILImage
+from scraper import ScraperBot, ScraperBotConfig
+from helpers import starts_with_quotes, get_start_end_quotes
+from dataclasses import dataclass
+from datasets import Image
+
+
+@dataclass(frozen=True)
+class HFDatasetScheme:
+    caption: str
+    image: Image(decode=True)
+    link: str
+    message_id: str
+    timestamp: str
+
+
+url_pattern = re.compile(r'https?://\S+')
+
+
+def parse_fn(message: Dict[str, Any]) -> List[HFDatasetScheme]:
+    """Parses a message into a list of Hugging Face Dataset Schemes.
+
+    Parameters
+    ----------
+    message : Dict[str, Any]
+        The message to parse.
+
+    Returns
+    -------
+    List[HFDatasetScheme]
+        A list of Hugging Face Dataset Schemes.
+    """
+    content = message["content"]
+
+    (first_quote_index, last_quote_index) = get_start_end_quotes(content)
+
+    # Extract the text between the first and last quotes to get the complete prompt
+    prompt = content[first_quote_index + 1:last_quote_index].strip()
+    image_urls = url_pattern.findall(content)
+    timestamp = message["timestamp"]
+    message_id = message["id"]
+
+    return [HFDatasetScheme(caption=prompt, image=None, link=image_url, message_id=message_id, timestamp=timestamp)
+            for image_url in image_urls]
+
+
+def condition_fn(message: Dict[str, Any]) -> bool:
+    """Checks if a message meets the condition to be parsed.
+
+    Parameters
+    ----------
+    message : Dict[str, Any]
+        The message to check.
+
+    Returns
+    -------
+    bool
+        True if the message meets the condition, False otherwise.
+    """
+    return url_pattern.search(message["content"]) and starts_with_quotes(message["content"])
+
+
+def prepare_dataset(messages: List[HFDatasetScheme]) -> pd.DataFrame:
+    return pd.DataFrame(
+        {
+            "caption": [msg.caption for msg in messages],
+            "image": [
+                None for msg in messages
+            ],  # Initialize to None, will be filled in later
+            "link": [
+                msg.link for msg in messages
+            ],  # will maintain just because we use it to filter
+            "message_id": [msg.message_id for msg in messages],
+            "timestamp": [msg.timestamp for msg in messages],
+        }
+    )
+
+
+def get_image(link: str) -> bytes:
+    image = PILImage.open(requests.get(link, stream=True).raw).convert("RGB")
+    img_byte_arr = io.BytesIO()
+    image.save(img_byte_arr, format="PNG")
+    return {"bytes": img_byte_arr.getvalue(), "path": None}
+
+
+if __name__ == "__main__":
+    config_path = os.path.join(os.path.dirname(__file__), "config.json")
+    config = ScraperBotConfig.from_json(config_path)
+
+    bot = ScraperBot(config=config, HFDatasetScheme=HFDatasetScheme, prepare_dataset=prepare_dataset, parse_fn=parse_fn, condition_fn=condition_fn, download_fn=get_image)
+    bot.scrape(fetch_all=os.environ.get("FETCH_ALL", "false").lower() == "true")