gpt4free

公开

关注 0 Fork 0 Star 1

返回提交历史

XFEstudio/gpt4free

Fix url download function

6314d27d

hlohaus <983577+hlohaus@users.noreply.github.com>

提交于 2025-02-22 14:20

父提交 6ba21db

代码差异

3 个文件 +6 -6

Modified g4f/gui/client/static/js/chat.v1.js +1 -1

@@ -402,7 +402,7 @@ const handle_ask = async (do_ask_gpt = true) => {

402 402 await add_conversation(window.conversation_id);

403 403

404 404 // Is message a url?

405

    const expression = /https?:\/\/(www\.)?[-a-zA-Z0-9@:%._\+~#=]{1,256}\.[a-zA-Z0-9()]{1,6}\b([-a-zA-Z0-9()@:%_\+.~#?&//=]*)/gi;

405

    const expression = /^https?:\/\/(www\.)?[-a-zA-Z0-9@:%._\+~#=]{1,256}\.[a-zA-Z0-9()]{1,6}\b([-a-zA-Z0-9()@:%_\+.~#?&//=]*)$/gi;

406 406 const regex = new RegExp(expression);

407 407 if (message.match(regex)) {

408 408 paperclip.classList.add("blink");

Modified g4f/tools/files.py +3 -3

@@ -416,7 +416,7 @@ def read_links(html: str, base: str) -> set[str]:

416 416 async def download_urls(

417 417 bucket_dir: Path,

418 418 urls: list[str],

419 max_depth: int = 1,

419 max_depth: int = 0,

420 420 loading_urls: set[str] = set(),

421 421 lock: asyncio.Lock = None,

422 422 delay: int = 3,

@@ -515,7 +515,7 @@ def stream_chunks(bucket_dir: Path, delete_files: bool = False, refine_chunks_wi

515 515 if refine_chunks_with_spacy:

516 516 for chunk in stream_read_parts_and_refine(bucket_dir, delete_files):

517 517 if event_stream:

518 size += len(chunk.decode('utf-8'))

518 size += len(chunk.encode())

519 519 yield f'data: {json.dumps({"action": "refine", "size": size})}\n\n'

520 520 else:

521 521 yield chunk

@@ -524,7 +524,7 @@ def stream_chunks(bucket_dir: Path, delete_files: bool = False, refine_chunks_wi

524 524 streaming = cache_stream(streaming, bucket_dir)

525 525 for chunk in streaming:

526 526 if event_stream:

527 size += len(chunk.decode('utf-8'))

527 size += len(chunk.encode())

528 528 yield f'data: {json.dumps({"action": "load", "size": size})}\n\n'

529 529 else:

530 530 yield chunk

Modified g4f/tools/web_search.py +2 -2

@@ -89,10 +89,10 @@ def scrape_text(html: str, max_words: int = None, add_source=True, count_images:

89 89 if select:

90 90 select.extract()

91 91

92 image_select = "img[alt][src^=http]:not([alt='']):not(.avatar)"

92 image_select = "img[alt][src^=http]:not([alt='']):not(.avatar):not([width])"

93 93 image_link_select = f"a:has({image_select})"

94 94 yield_words = []

    for paragraph in soup.select(f"h1, h2, h3, h4, h5, h6, p, table:not(:has(p)), ul:not(:has(p)), {image_link_select}"):

    for paragraph in soup.select(f"h1, h2, h3, h4, h5, h6, p, pre, table:not(:has(p)), ul:not(:has(p)), {image_link_select}"):

96 96 if count_images > 0:

97 97 image = paragraph.select_one(image_select)

98 98 if image: