PgsFile 0.1.4__py3-none-any.whl → 0.1.5__py3-none-any.whl

PgsFile/PgsFile.py

@@ -1406,3 +1406,49 @@ class PGScraper(object):
         else:
             print(r.status_code,"invalid url",url)            
             return all_want_list   
+
+
+# -*- coding: utf-8 -*-
+"""
+Created on Thu Sep 17 16:11:45 2020
+Showing download progress and speed when audio-visual files like MP4, MP3, JPG etc are downloading!
+@author: Petercusin
+"""
+
+import time
+from contextlib import closing 
+
+def audiovisual_downloader(url, path):
+    with closing(requests.get(url, stream=True, headers=my_headers)) as r:
+        chunk_size=1024*10
+        content_size=int(r.headers['content-length'])
+        print('Initiating download...')
+        with open(path, "wb") as f:
+            p=ProgressData(size=content_size, unit='Kb', block=chunk_size)
+            for chunk in r.iter_content(chunk_size=chunk_size):
+                f.write(chunk)
+                p.output()
+ 
+class ProgressData(object):
+    def __init__(self, block,size, unit, file_name='', ):
+        self.file_name=file_name
+        self.block=block/1000.0
+        self.size=size/1000.0
+        self.unit=unit
+        self.count=0
+        self.start=time.time()
+    def output(self):
+        self.end=time.time()
+        self.count += 1
+        speed=self.block/(self.end-self.start) if (self.end-self.start)>0 else 0
+        self.start=time.time()
+        loaded=self.count*self.block
+        progress=round(loaded/self.size, 4)
+        if loaded >= self.size:
+            print(u'%sYour download has finished successfully.\r\n'%self.file_name)
+        else:
+            print(u'{0}Download Progress: {1:.2f}{2}/{3:.2f}{4} {5:.2%} Download Speed: {6:.2f}{7}/s'.\
+                  format(self.file_name, loaded, self.unit,\
+                  self.size, self.unit, progress, speed, self.unit))
+            print('%50s'%('/'*int((1-progress)*50)))
+

PgsFile/__init__.py

@@ -1,4 +1,5 @@
 from .PgsFile import PGScraper
+from .PgsFile import audiovisual_downloader
 
 from .PgsFile import install_package, uninstall_package
 from .PgsFile import run_script, run_command

{PgsFile-0.1.4.dist-info → PgsFile-0.1.5.dist-info}/METADATA

@@ -1,7 +1,7 @@
 Metadata-Version: 2.1
 Name: PgsFile
-Version: 0.1.4
-Summary: This module aims to simplify Python package management, script execution, file handling, web scraping, data cleaning, and word list generation for literary students, making it more accessible and convenient to use.
+Version: 0.1.5
+Summary: This module aims to simplify Python package management, script execution, file handling, web scraping, multimedia download, data cleaning, and word list generation for literary students, making it more accessible and convenient to use.
 Home-page: https://mp.weixin.qq.com/s/F94jyCBOQ3VmiPmSjv6ZAw
 Author: Pan Guisheng
 Author-email: 895284504@qq.com
@@ -34,7 +34,7 @@ Function 5: This library provides support for common text cleaning tasks, such a
 
 Function 6: It also manages Python package installations and uninstallations, and allows running scripts and commands in Python interactive command lines instead of Windows command prompt.
 
-Function 7: This is extremely beneficial for scraping newspaper data using PGScraper.
+Function 7: Download audiovisual files like videos, images, and audio using audiovisual_downloader, which is extremely useful and efficient. Additionally, scrape newspaper data with PGScraper, a highly efficient tool for this purpose.
 
 Table 1: The directory and size of Pgs-Corpora
 ├── Idioms (1, 171.78 KB)

{PgsFile-0.1.4.dist-info → PgsFile-0.1.5.dist-info}/RECORD

@@ -1,5 +1,5 @@
-PgsFile/PgsFile.py,sha256=MJDO16jtUglvGNCosdfeILa96UGPiShCp52VAJ0PsVg,59834
-PgsFile/__init__.py,sha256=bu0BNgzYNRNpbZAFhvLo-S3npg8kasLam1n9VkiCQNQ,1546
+PgsFile/PgsFile.py,sha256=T7O755N1kyi5OTJpjH8bsPqMBZrtsg5iPAqgK11l7mA,61528
+PgsFile/__init__.py,sha256=nLukVrf9DO6wblmBsgfsPU90xULZ6AQrFOmjMC8Skio,1591
 PgsFile/Corpora/Idioms/English_Idioms_8774.txt,sha256=qlsP0yI_XGECBRiPZuLkGZpdasc77sWSKexANu7v8_M,175905
 PgsFile/Corpora/Monolingual/Chinese/People's Daily 20130605/Raw/00000000.txt,sha256=SLGGSMSb7Ff1RoBstsTW3yX2wNZpqEUchFNpcI-mrR4,1513
 PgsFile/Corpora/Monolingual/Chinese/People's Daily 20130605/Raw/00000001.txt,sha256=imOa6UoCOIZoPXT4_HNHgCUJtd4FTIdk2FZNHNBgJyg,3372
@@ -2618,8 +2618,8 @@ PgsFile/models/slovene.pickle,sha256=faxlAhKzeHs5mWwBvSCEEVST5vbsOQurYfdnUlsIuOo
 PgsFile/models/spanish.pickle,sha256=Jx3GAnxKrgVvcqm_q1ZFz2fhmL9PlyiVhE5A9ZiczcM,597831
 PgsFile/models/swedish.pickle,sha256=QNUOva1sqodxXy4wCxIX7JLELeIFpUPMSlaQO9LJrPo,1034496
 PgsFile/models/turkish.pickle,sha256=065H12UB0CdpiAnRLnUpLJw5KRBIhUM0KAL5Xbl2XMw,1225013
-PgsFile-0.1.4.dist-info/LICENSE,sha256=cE5c-QToSkG1KTUsU8drQXz1vG0EbJWuU4ybHTRb5SE,1138
-PgsFile-0.1.4.dist-info/METADATA,sha256=nF-Qqjy5N7mXswO_HrASmMFEBXjmI_jNjr5Z3OcxemI,4697
-PgsFile-0.1.4.dist-info/WHEEL,sha256=pkctZYzUS4AYVn6dJ-7367OJZivF2e8RA9b_ZBjif18,92
-PgsFile-0.1.4.dist-info/top_level.txt,sha256=028hCfwhF3UpfD6X0rwtWpXI1RKSTeZ1ALwagWaSmX8,8
-PgsFile-0.1.4.dist-info/RECORD,,
+PgsFile-0.1.5.dist-info/LICENSE,sha256=cE5c-QToSkG1KTUsU8drQXz1vG0EbJWuU4ybHTRb5SE,1138
+PgsFile-0.1.5.dist-info/METADATA,sha256=U1aOqNmJ9hsgSsRGkAniXwAaYggDedGf1YI6V-YZtx0,4867
+PgsFile-0.1.5.dist-info/WHEEL,sha256=eOLhNAGa2EW3wWl_TU484h7q1UNgy0JXjjoqKoxAAQc,92
+PgsFile-0.1.5.dist-info/top_level.txt,sha256=028hCfwhF3UpfD6X0rwtWpXI1RKSTeZ1ALwagWaSmX8,8
+PgsFile-0.1.5.dist-info/RECORD,,

{PgsFile-0.1.4.dist-info → PgsFile-0.1.5.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: bdist_wheel (0.40.0)
+Generator: bdist_wheel (0.44.0)
 Root-Is-Purelib: true
 Tag: py3-none-any