Code Needs finishing Off Help Needed

[eddywinch82]

I need help, with finishing of the following code :- which is not all my own work, i am not this good at programming,
but had help with it yesterday :-

from bs4 import BeautifulSoup
import requests, wget, re, zipfile, io


def get_zips(link_root, zips_suffix):
    # 'http://web.archive.org/web/20050315112710/http://www.projectai.com:80/libraries/repaints.php?ac=89&cat=6'
    zips_page =  link_root + zips_suffix
    # print zips_page
    zips_source = requests.get(zips_page).text
    zip_soup = BeautifulSoup(zips_source, "html.parser")
    for zip_file in zip_soup.select("a[href*=download.php?fileid=]"):
        zip_url = link_root + zip_file['href']
        print('downloading', zip_file.text, '...',)
        r = requests.get(zip_url)
        with open(zip_file.text, 'wb') as zipFile:
            zipFile.write(r.content)


def download_links(root, cat):
    url = ''.join([root, cat])
    source_code = requests.get(url)
    plain_text = source_code.text
    soup = BeautifulSoup(plain_text, "html.parser")

    for zips_suffix in soup.select("a[href*=repaints.php?ac=]"):
        get_zips(root, zips_suffix['href'])


link_root = 'http://web.archive.org/web/20041225023002/http://www.projectai.com:80/libraries/'

# Example category, need to read all categories from first page into a list and iterate categories
category = 'acfiles.php?cat=6'
download_links(link_root, category)

This is the path for one of the Aircraft catagories :- 'http://web.archive.org/web/20050315112710/http://www.projectai.com:80/libraries/repaints.php?ac=89&cat=6'

But there are several, where the last part of the path is always :- /repaints.php?ac=Two Digit Number@cat=6

What do i need to type, to download all the .zip Files from http://web.archive.org/web/2005031511271...c=89&cat=6, without having to type each different ac=Two Digit Number@cat=6 for that path each time? Any help would be much appreciated.

[snippsat]

Here some hints.

from bs4 import BeautifulSoup
import requests

url = 'http://web.archive.org/web/20041114195147/http://www.projectai.com:80/libraries/repaints.php?ac=89&cat=6'
url_get = requests.get(url)
soup = BeautifulSoup(url_get.content, 'lxml')
td = soup.find_all('td', class_="text", colspan="2")

Look at td:

>>> td
[<td bgcolor="#FFFF99" class="text" colspan="2"><a href="download.php?fileid=6082">Texture.ABR-Air Contractors A30B_PW CONTRACT.zip</a> </td>,
 <td bgcolor="#FFCC99" class="text" colspan="2"><a href="download.php?fileid=6177">Texture.AHK-Air Hong Kong A300B AIR HONG KONG.zip</a> </td>,
 <td bgcolor="#FFFF99" class="text" colspan="2"><a href="download.php?fileid=6084">Texture.FPO-Europe Airpost A30B_GE FRENCH POST.zip</a> </td>,
 <td bgcolor="#FFCC99" class="text" colspan="2"><a href="download.php?fileid=7223">Texture.HDA-Dragonair Cargo A30BGE DRAGONAIR.zip</a> </td>]
>>> for h in td:
...     h.a.get('href')
...     
'download.php?fileid=6082'
'download.php?fileid=6177'
'download.php?fileid=6084'
'download.php?fileid=7223'

So now have all fileid for download,the whole url is the same before,
so 6082 is one .zip and change to 6177 is an other .zip file.

[eddywinch82]

I have adapted the working Code, for a different Flight Sim Website Link, but when I run the Code, there are no Traceback Errors, but on investigation no .zip Files appear to be downloading. unless they are ? Have I gone wrong somewhere ? :-

from bs4 import BeautifulSoup
import requests, wget, re, zipfile, io


def get_zips(link_root, zips_suffix):
    # 'http://web.archive.org/web/20050315112710/http://www.projectai.com:80/libraries/repaints.php?ac=89&cat=6'
    zips_page =  link_root + zips_suffix
    # print zips_page
    zips_source = requests.get(zips_page).text
    zip_soup = BeautifulSoup(zips_source, "html.parser")
    for zip_file in zip_soup.select("a[href*=download_model.php?fileid=]"):
        zip_url = link_root + zip_file['href']
        print('downloading', zip_file.text, '...',)
        r = requests.get(zip_url)
        with open(zip_file.text, 'wb') as zipFile:
            zipFile.write(r.content)


def download_links(root, cat):
    url = ''.join([root, cat])
    source_code = requests.get(url)
    plain_text = source_code.text
    soup = BeautifulSoup(plain_text, "html.parser")
    td = soup.find_all('td', class_="text", colspan="2", bgcolour="#FFFF99", href="download_model.php?fileid=")
    for h in td:
         h.a.get('href')

link_root = 'http://web.archive.org/web/20050308033321/http://www.projectai.com:80/packages/fde.php'

[snippsat]

You don't call functions,then nothing will be happening.
download_links function is missing root and cat argument and it don't return anything.

[eddywinch82]

I see what you mean, category = 'acfiles.php?cat=6' i tried category ='fde.php' but as it wasn't a category it didn't download .zip files, if cat = category what word should be used for php folder extensions ?

Also I have installed the Axel Download accelerator into Python, but I am not sure what to type to make it speed up all the .zip file downloads, when I run the modules ? I found the following on a website :- from axel import axel

# Download http://someurl/file.zip with 500 parallel connection
file_path = axel('http://someurl/file.zip', num_connections=500)

[eddywinch82]

from bs4 import BeautifulSoup
import requests, wget, re, zipfile, io
 
 
def get_zips(link_root, zips_suffix):
    # 'http://web.archive.org/web/20050315112710/http://www.projectai.com:80/libraries/repaints.php?ac=89&cat=6'
    zips_page =  link_root + zips_suffix
    # print zips_page
    zips_source = requests.get(zips_page).text
    zip_soup = BeautifulSoup(zips_source, "html.parser")
    for zip_file in zip_soup.select("a[href*=download.php?fileid=]"):
        zip_url = link_root + zip_file['href']
        print('downloading', zip_file.text, '...',)
        r = requests.get(zip_url)
        with open(zip_file.text, 'wb') as zipFile:
            zipFile.write(r.content)
 
 
def download_links(root, cat):
    url = ''.join([root, cat])
    source_code = requests.get(url)
    plain_text = source_code.text
    soup = BeautifulSoup(plain_text, "html.parser")
    td = soup.find_all('td', class_="text", colspan="2", bgcolour="#FFFF99", href="download.php?fileid=")
    for h in td:
         h.a.get('href')
 
    for zips_suffix in soup.select("a[href*=repaints.php?ac=]"):
        get_zips(root, zips_suffix['href'])
 
 
link_root = 'http://web.archive.org/web/20041225023002/http://www.projectai.com:80/libraries/'
 
# Example category, need to read all categories from first page into a list and iterate categories
category = 'acfiles.php?cat=6'
download_links(link_root, category)

[snippsat]

need to read all categories from first page into a list and iterate categories

Example:

from bs4 import BeautifulSoup
import requests

url = 'http://web.archive.org/web/20041225023002/http://www.projectai.com:80/libraries/acfiles.php?cat=6'
url_get = requests.get(url)
soup = BeautifulSoup(url_get.content, 'lxml')
td = soup.find_all('td', width="50%")
all_plains = [link.find('a').get('href') for link in td]
print(all_plains)

Also I have installed the Axel Download accelerator into Python, but I am not sure what to type to make it speed up all the .zip file downloads, when I run the modules ?

I have not heard of Alex.
I write my own for this,but it's a more advance topic.
Can show example with concurrent.futures,that i like to use for this.

import requests
import concurrent.futures

def download(number_id):
    a_zip = 'http://web.archive.org/web/20041205075703/http://www.projectai.com:80/packages/download_model.php?eula=1&fileid={}'.format(number_id)
    with open('{}.zip'.format(number_id), 'wb') as f:
        f.write(requests.get(a_zip).content)

if __name__ == '__main__':
    file_id = list(range(1,50))
    with concurrent.futures.ProcessPoolExecutor(max_workers=10) as executor:
        for number_id in file_id:
            executor.submit(download, number_id)

Without it takes 4-5 minute to download,now it take 30-sec.

[eddywinch82]

Error:
Exception in thread Thread-1:
Traceback (most recent call last):
  File "C:\Python34\Lib\threading.py", line 920, in _bootstrap_inner
    self.run()
  File "C:\Python34\Lib\threading.py", line 868, in run
    self._target(*self._args, **self._kwargs)
  File "C:\Python34\Lib\concurrent\futures\process.py", line 251, in _queue_management_worker
    shutdown_worker()
  File "C:\Python34\Lib\concurrent\futures\process.py", line 209, in shutdown_worker
    call_queue.put_nowait(None)
  File "C:\Python34\Lib\multiprocessing\queues.py", line 131, in put_nowait
    return self.put(obj, False)
  File "C:\Python34\Lib\multiprocessing\queues.py", line 82, in put
    raise Full
queue.Full

I get that traceback and then the .zip Files start downloading at the normal speed not quicker. What is the Traceback Text meaning ? Eddie

Also for one of the Website links :- I have the following Code

from bs4 import BeautifulSoup
import requests, zipfile, io, concurrent.futures

def download(number_id):
    a_zip = 'http://web.archive.org/web/20050301025710//http://www.projectai.com:80/packages/download_model.php?eula=1&fileid={}'.format(number_id)
    with open('{}.zip'.format(number_id), 'wb') as f:
        f.write(requests.get(a_zip).content)
 
if __name__ == '__main__':
    file_id = list(range(1,50))
    with concurrent.futures.ProcessPoolExecutor(max_workers=10) as executor:
        for number_id in file_id:
            executor.submit(download, number_id)

def get_zips(link_root, zips_suffix):
    # 'http://web.archive.org/web/20050315112710/http://www.projectai.com:80/libraries/repaints.php?ac=89&cat=6'
    zips_page =  link_root + zips_suffix
    # print zips_page
    zips_source = requests.get(zips_page).text
    zip_soup = BeautifulSoup(zips_source, "html.parser")
    for zip_file in zip_soup.select("a[href*=download.php?fileid=]"):
        zip_url = link_root + zip_file['href']
        print('downloading', zip_file.text, '...',)
        r = requests.get(zip_url)
        with open(zip_file.text, 'wb') as zipFile:
            zipFile.write(r.content)

def download_links(root, cat):
    url = ''.join([root, cat])
    source_code = requests.get(url)
    plain_text = source_code.text
    soup = BeautifulSoup(plain_text, "html.parser")

link_root = 'http://web.archive.org/web/20050301025710/http://www.projectai.com:80/packages/'

category ='fde.php'
download_links(link_root,category)

but .zip files are not being saved with the proper .zip File name as 49.zip 50.zip 51.zip etc and they say 0 bytes. Or is that because they havn't finished downloading ? Eddie

---

Also for one of the Website links :- I have the following Code

from bs4 import BeautifulSoup
import requests, zipfile, io, concurrent.futures

def download(number_id):
    a_zip = 'http://web.archive.org/web/20050301025710//http://www.projectai.com:80/packages/download_model.php?eula=1&fileid={}'.format(number_id)
    with open('{}.zip'.format(number_id), 'wb') as f:
        f.write(requests.get(a_zip).content)
 
if __name__ == '__main__':
    file_id = list(range(1,50))
    with concurrent.futures.ProcessPoolExecutor(max_workers=10) as executor:
        for number_id in file_id:
            executor.submit(download, number_id)

def get_zips(link_root, zips_suffix):
    # 'http://web.archive.org/web/20050315112710/http://www.projectai.com:80/libraries/repaints.php?ac=89&cat=6'
    zips_page =  link_root + zips_suffix
    # print zips_page
    zips_source = requests.get(zips_page).text
    zip_soup = BeautifulSoup(zips_source, "html.parser")
    for zip_file in zip_soup.select("a[href*=download.php?fileid=]"):
        zip_url = link_root + zip_file['href']
        print('downloading', zip_file.text, '...',)
        r = requests.get(zip_url)
        with open(zip_file.text, 'wb') as zipFile:
            zipFile.write(r.content)

def download_links(root, cat):
    url = ''.join([root, cat])
    source_code = requests.get(url)
    plain_text = source_code.text
    soup = BeautifulSoup(plain_text, "html.parser")

link_root = 'http://web.archive.org/web/20050301025710/http://www.projectai.com:80/packages/'

category ='fde.php'
download_links(link_root,category)

but .zip files are not being saved with the proper .zip File name, they are being saved as 49.zip 50.zip 51.zip etc and they say 0 bytes. Or is that because they havn't finished downloading ? Eddie

---

Sorry they are being saved as 49.zip 50.zip 51.zip etc

[buran]

but .zip files are not being saved with the proper .zip File name, they are being saved as 49.zip 50.zip 51.zip etc and they say 0 bytes. Or is that because they havn't finished downloading ? Eddie

No, it's because that is how you construct the file name in download function (see line#6)

[eddywinch82]

what do I need to type, so that the Files download, with the proper .zip File name ?