motebaya / picuki Goto Github PK

Traceback (most recent call last):
  File "\Picuki\cli.py", line 139, in <module>
    asyncio.run(CLI._main(**vars(args)))
  File "C:\Python310\lib\asyncio\runners.py", line 44, in run
    return loop.run_until_complete(main)
  File "C:\Python310\lib\asyncio\base_events.py", line 641, in run_until_complete
    return future.result()
  File "\Picuki\cli.py", line 40, in _main
    await Main.downloadMediaContent(
  File "\Picuki\main.py", line 126, in downloadMediaContent
    await Helper._downloadContent(
  File "\Picuki\lib\Helper.py", line 179, in _downloadContent
    f"{output}/{media_type}", Helper.get_valid_filename(
  File "\Picuki\lib\Helper.py", line 116, in get_valid_filename
    if (basename := re.search(r"^https?\:\/\/[^<]+\/q\/(?P<filename>[^\"].*?)\|\|", url)):        
  File "C:\Python310\lib\re.py", line 200, in search
    return _compile(pattern, flags).search(string)
TypeError: expected string or bytes-like object

I thinks it's gona solve this problem:

main.py:126

                            if('url' in cont):
                                cont = cont['url']

using the command:

python main.py -u zuck -i

the excution stops with the following error

14:50:07 info:getting content from: 3097159049866530005 [13 of 24]
Traceback (most recent call last):
File "/usr/local/lib/python3.10/site-packages/anyio/streams/tls.py", line 130, in _call_sslobject_method
result = func(*args)
File "/usr/local/lib/python3.10/ssl.py", line 916, in read
v = self._sslobj.read(len)
ssl.SSLWantReadError: The operation did not complete (read) (_ssl.c:2536)

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "/usr/local/lib/python3.10/site-packages/httpcore/backends/asyncio.py", line 34, in read
return await self._stream.receive(max_bytes=max_bytes)
File "/usr/local/lib/python3.10/site-packages/anyio/streams/tls.py", line 195, in receive
data = await self._call_sslobject_method(self._ssl_object.read, max_bytes)
File "/usr/local/lib/python3.10/site-packages/anyio/streams/tls.py", line 137, in _call_sslobject_method
data = await self.transport_stream.receive()
File "/usr/local/lib/python3.10/site-packages/anyio/_backends/_asyncio.py", line 1265, in receive
await self._protocol.read_event.wait()
File "/usr/local/lib/python3.10/asyncio/locks.py", line 213, in wait
await fut
asyncio.exceptions.CancelledError

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "/usr/local/lib/python3.10/site-packages/httpcore/_exceptions.py", line 10, in map_exceptions
yield
File "/usr/local/lib/python3.10/site-packages/httpcore/backends/asyncio.py", line 32, in read
with anyio.fail_after(timeout):
File "/usr/local/lib/python3.10/site-packages/anyio/_core/_tasks.py", line 118, in exit
raise TimeoutError
TimeoutError

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "/usr/local/lib/python3.10/site-packages/httpx/_transports/default.py", line 60, in map_httpcore_exceptions
yield
File "/usr/local/lib/python3.10/site-packages/httpx/_transports/default.py", line 353, in handle_async_request
resp = await self._pool.handle_async_request(req)
File "/usr/local/lib/python3.10/site-packages/httpcore/_async/connection_pool.py", line 253, in handle_async_request
raise exc
File "/usr/local/lib/python3.10/site-packages/httpcore/_async/connection_pool.py", line 237, in handle_async_request
response = await connection.handle_async_request(request)
File "/usr/local/lib/python3.10/site-packages/httpcore/_async/connection.py", line 90, in handle_async_request
return await self._connection.handle_async_request(request)
File "/usr/local/lib/python3.10/site-packages/httpcore/_async/http11.py", line 112, in handle_async_request
raise exc
File "/usr/local/lib/python3.10/site-packages/httpcore/_async/http11.py", line 91, in handle_async_request
) = await self._receive_response_headers(**kwargs)
File "/usr/local/lib/python3.10/site-packages/httpcore/_async/http11.py", line 155, in _receive_response_headers
event = await self._receive_event(timeout=timeout)
File "/usr/local/lib/python3.10/site-packages/httpcore/_async/http11.py", line 191, in _receive_event
data = await self._network_stream.read(
File "/usr/local/lib/python3.10/site-packages/httpcore/backends/asyncio.py", line 31, in read
with map_exceptions(exc_map):
File "/usr/local/lib/python3.10/contextlib.py", line 153, in exit
self.gen.throw(typ, value, traceback)
File "/usr/local/lib/python3.10/site-packages/httpcore/_exceptions.py", line 14, in map_exceptions
raise to_exc(exc)
httpcore.ReadTimeout

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
File "/root/New/Picuki/main.py", line 274, in
asyncio.run(_main(
File "/usr/local/lib/python3.10/asyncio/runners.py", line 44, in run
return loop.run_until_complete(main)
File "/usr/local/lib/python3.10/asyncio/base_events.py", line 641, in run_until_complete
return future.result()
File "/root/New/Picuki/main.py", line 204, in _main
if (content := await module.get_media_content(media)):
File "/root/New/Picuki/lib/Picuki.py", line 117, in get_media_content
page = await self.get("/media/{}".format(
File "/usr/local/lib/python3.10/site-packages/httpx/_client.py", line 1757, in get
return await self.request(
File "/usr/local/lib/python3.10/site-packages/httpx/_client.py", line 1533, in request
return await self.send(request, auth=auth, follow_redirects=follow_redirects)
File "/usr/local/lib/python3.10/site-packages/httpx/_client.py", line 1620, in send
response = await self._send_handling_auth(
File "/usr/local/lib/python3.10/site-packages/httpx/_client.py", line 1648, in _send_handling_auth
response = await self._send_handling_redirects(
File "/usr/local/lib/python3.10/site-packages/httpx/_client.py", line 1685, in _send_handling_redirects
response = await self._send_single_request(request)
File "/usr/local/lib/python3.10/site-packages/httpx/_client.py", line 1722, in _send_single_request
response = await transport.handle_async_request(request)
File "/usr/local/lib/python3.10/site-packages/httpx/_transports/default.py", line 352, in handle_async_request
with map_httpcore_exceptions():
File "/usr/local/lib/python3.10/contextlib.py", line 153, in exit
self.gen.throw(typ, value, traceback)
File "/usr/local/lib/python3.10/site-packages/httpx/_transports/default.py", line 77, in map_httpcore_exceptions
raise mapped_exc(message) from exc
httpx.ReadTimeout

the error happens always when the process get the 12th or 13th post with all the username.

I suggest the following improvement:

when the information are collected the system write the box with captions etc, it wil be possible to save those information in a json file using a new option like -s in arguments this will be usefull to manage data for other purpose.
In addition it will be very important to add in json file created the name of the file/files images downloaded that now loose the link between file and message.

Thank You

can you fix the code ? i'am not expert in coding, but i know next page link has moved to
<input class="pagination-next-page-input" type="hidden" value="

After making request to <div class="load-more-wrapper" data-next="/app/controllers/ajax.php?type=profile&end_cursor=QVFBcU1oSHJSY2U0WElXSWpjOUx4WUxac2RCTWh1TlRpdS1vMUFaU2NxRTNZSmVWYVRVckhWdG92OVFqckFIUEZiNnljNFN2M2dQVUN1cjlOTDBieE9PMQ==&end_cursor_mobile=3161282768902553987_3217616838&id=3217616838&ads=1"> the next page link will be in the page of ajax.php not in homepage

thanks a lot.

python main.py -u zuck -v
14:54:43 debug:Using selector: EpollSelector
╭─────── information ────────╮
│ bio: │
│ followers: 12,007,194 │
│ following: 523 │
│ full_name: Mark Zuckerberg │
│ total_posts: 284 │
│ username: @zuck │
╰────────────────────────────╯
14:54:44 info:media ID collected: 12
14:54:44 Warning:loading more page....
14:54:44 info:media ID collected: 24
14:54:44 info:Total Media Collected: 24
14:54:44 info:Selected media: ['videos'], starting download..
14:54:44 info:getting content from: 3144049196777682809 [1 of 24]
╭────────────────────────────────────────────────────────────────────── information ──────────────────────────────────────────────────────────────────────╮
│ caption: Threads reached 100 million sign ups this weekend -- within five days of launching. Thanks to all of you who are making this fun and friendly! │
│ comments_count: 3,947 │
│ likes_count: 142,286 likes │
│ name: @zuck │
│ time: 1 day ago │
╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
14:54:45 Warning:there's no videos or thumbnails to download..
14:54:45 info:getting content from: 3140520095901479927 [2 of 24]
╭────────────────────────────────────────────────────────────────────────────────────────────────── information ───────────────────────────────────────────────────────────────────────────────────────────────────╮
│ caption: Meet Threads, an open and friendly public space for conversation. Our vision is to take the best parts of Instagram and create a new experience for text, ideas, and discussing what's on your mind. I │
│ think the world needs this kind of friendly community, and I'm grateful to all of you who are part of Threads from day one. Threads is available in the app store now. │
│ comments_count: 24,342 │
│ likes_count: 719,652 likes │
│ name: @zuck │
│ time: 6 days ago │
╰──────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
14:54:45 info:Total videos/thumbnails Collected: 1
14:54:45 info:downloading videos ( 1 of 1)
Completed..saved as: /root/New/Picuki/zuck/videos/Y8SaNcuF32xYNKj0hSxjBnfed.mp4
14:54:46 info:getting content from: 3140510476081615763 [3 of 24]
╭──────────────── information ────────────────╮
│ caption: Threads is here. Let's do this. 🔥 │
│ comments_count: 7,262 │
│ likes_count: 347,005 likes │
│ name: @zuck │
│ time: 6 days ago │
╰─────────────────────────────────────────────╯
14:54:47 Warning:there's no videos or thumbnails to download..
14:54:47 info:getting content from: 3139898623990367685 [4 of 24]
╭──────────────────────────────────────────────────────────────────────────────────────────────── information ─────────────────────────────────────────────────────────────────────────────────────────────────╮
│ caption: Happy July 4th! 🇺🇸 Lots to be grateful for this year. As the big girls get older, I love talking to them about why America is so great. Looking forward to discussing with little Aurelia soon too. │
│ comments_count: 7,038 │
│ likes_count: 626,312 likes │
│ name: @zuck │
│ time: 1 week ago │
╰──────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
14:54:47 Warning:there's no videos or thumbnails to download..
14:54:47 info:getting content from: 3127421898368101810 [5 of 24]
╭───────────────────────────────────────────────── information ─────────────────────────────────────────────────╮
│ caption: Great learning from jiu jitsu legend @mikeymusumeci... and starting to prepare for our MMA debuts 😉 │
│ comments_count: 7,425 │
│ likes_count: 206,400 likes │
│ name: @zuck │
│ time: 3 weeks ago │
╰───────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
14:54:48 info:Total videos/thumbnails Collected: 1
14:54:48 info:downloading videos ( 1 of 1)
Completed..saved as: /root/New/Picuki/zuck/videos/uNhxneZ0LIYDd9NGmIH2W5BjN.mp4
14:54:49 info:getting content from: 3120828822040437226 [6 of 24]
╭───────────────────────────────────────────────────────────────────────── information ──────────────────────────────────────────────────────────────────────────╮
│ caption: Great to be back in person in Hacker Square for Meta's All Hands! So much energy and excitement for building the future of human connection together. │
│ comments_count: 3,372 │
│ likes_count: 98,093 likes │
│ name: @zuck │
│ time: 1 month ago │
╰────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
14:54:49 info:Total videos/thumbnails Collected: 1
14:54:49 info:downloading videos ( 1 of 1)
Traceback (most recent call last):
File "/root/New/Picuki/main.py", line 274, in
asyncio.run(_main(
File "/usr/local/lib/python3.10/asyncio/runners.py", line 44, in run
return loop.run_until_complete(main)
File "/usr/local/lib/python3.10/asyncio/base_events.py", line 641, in run_until_complete
return future.result()
File "/root/New/Picuki/main.py", line 236, in _main
await _download(
File "/root/New/Picuki/main.py", line 58, in _download
assert url is not None, "stopped, nothing url to download!"
AssertionError: stopped, nothing url to download!

the program download the firt and second video ad the crash with error