pywaybackup 1.2.6__tar.gz → 1.3.0__tar.gz

{pywaybackup-1.2.6/pywaybackup.egg-info → pywaybackup-1.3.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: pywaybackup
-Version: 1.2.6
+Version: 1.3.0
 Summary: Download snapshots from the Wayback Machine
 Home-page: https://github.com/bitdruid/python-wayback-machine-downloader
 Author: bitdruid
@@ -102,6 +102,10 @@ Path defaults to output-dir. Saves the result of CDX query as a file. Useful for
 - **`--cdxinject`** `<filepath>`:<br>
 Injects a CDX query file to download snapshots. Ensure the query matches the previous `--url` for correct folder structure.
 
+**Auto:**
+- **`--auto`**:<br>
+If set, csv, skip and cdxbackup/cdxinject are handled automatically. Keep the files and folders as they are. Otherwise they will not be recognized when restarting a download.
+
 ### Debug
 
 - `--debug`: If set, full traceback will be printed in case of an error. The full exception will be written into `waybackup_error.log`.

{pywaybackup-1.2.6 → pywaybackup-1.3.0}/README.md

@@ -86,6 +86,10 @@ Path defaults to output-dir. Saves the result of CDX query as a file. Useful for
 - **`--cdxinject`** `<filepath>`:<br>
 Injects a CDX query file to download snapshots. Ensure the query matches the previous `--url` for correct folder structure.
 
+**Auto:**
+- **`--auto`**:<br>
+If set, csv, skip and cdxbackup/cdxinject are handled automatically. Keep the files and folders as they are. Otherwise they will not be recognized when restarting a download.
+
 ### Debug
 
 - `--debug`: If set, full traceback will be printed in case of an error. The full exception will be written into `waybackup_error.log`.

pywaybackup-1.3.0/pywaybackup/__version__.py

@@ -0,0 +1 @@
+__version__ = "1.3.0"

{pywaybackup-1.2.6 → pywaybackup-1.3.0}/pywaybackup/archive.py

@@ -97,26 +97,28 @@ def print_list():
 # create filelist
 # timestamp format yyyyMMddhhmmss
 def query_list(url: str, range: int, start: int, end: int, explicit: bool, mode: str, cdxbackup: str, cdxinject: str):
-    if cdxinject:
-        try:
+
+    def inject(cdxinject):
+        if os.path.isfile(cdxinject):
             vb.write("\nInjecting CDX data...")
             cdxResult = open(cdxinject, "r")
             cdxResult = cdxResult.read()
-            vb.write(f"\n-----> {len(cdxResult)} snapshots injected")
-        except FileNotFoundError as e:
-            vb.write("\nFILE NOT FOUND -> could not inject CDX data")
-            os._exit(1)
-    else:
+            linecount = cdxResult.count("\n") - 1
+            vb.write(f"\n-----> {linecount} snapshots injected")
+            return cdxResult
+        else:
+            vb.write("\nNo CDX file found to inject - querying snapshots...")
+            return False
+
+    def query(url, range, start, end, explicit):
         vb.write("\nQuerying snapshots...")
         query_range = ""
-        
         if not range:
             if start: query_range = query_range + f"&from={start}"
             if end: query_range = query_range + f"&to={end}"
         else: 
             query_range = "&from=" + str(datetime.now().year - range)
 
-        # parse user input url and create according cdx url
         domain, subdir, filename = url_split(url)
         if domain and not subdir and not filename:
             cdx_url = f"*.{domain}/*" if not explicit else f"{domain}"
@@ -142,6 +144,12 @@ def query_list(url: str, range: int, start: int, end: int, explicit: bool, mode:
                 file.write(cdxResult)
                 vb.write("\n-----> CDX backup generated")
 
+        return cdxResult
+
+    if cdxinject:
+        cdxResult = inject(cdxinject)
+    if not cdxResult:
+        cdxResult = query(url, range, start, end, explicit)
     cdxResult = json.loads(cdxResult)
     sc.create_list(cdxResult, mode)
     vb.write(f"\n-----> {sc.count(collection=True)} snapshots to utilize")

{pywaybackup-1.2.6 → pywaybackup-1.3.0}/pywaybackup/arguments.py

@@ -36,6 +36,9 @@ def parse():
     exclusive_cdx.add_argument('--cdxbackup', type=str, nargs='?', const=True, metavar='path', help='Save the cdx query-result to a file for recurent use - defaults to output folder')
     exclusive_cdx.add_argument('--cdxinject', type=str, nargs='?', const=True, metavar='path', help='Inject a cdx backup-file to download according to the given url')
 
+    auto = parser.add_argument_group('auto')
+    auto.add_argument('--auto', action='store_true', help='includes automatic csv, skip and cdxbackup/cdxinject to resume a stopped download')
+
     args = parser.parse_args(args=None if sys.argv[1:] else ['--help']) # if no arguments are given, print help
     command = ' '.join(sys.argv[1:])
 

{pywaybackup-1.2.6 → pywaybackup-1.3.0}/pywaybackup/main.py

@@ -2,6 +2,7 @@ import os
 
 import signal
 
+import pywaybackup.helper as helper
 import pywaybackup.archive as archive
 
 from pywaybackup.arguments import parse
@@ -25,14 +26,20 @@ def main():
     if args.current:
         mode = "current"
 
-    if args.skip is True:
+    if args.auto:
         args.skip = args.output
-    if args.csv is True:
         args.csv = args.output
-    if args.cdxbackup is True:
         args.cdxbackup = args.output
-    if args.cdxinject is True:
-        args.cdxinject = args.output
+        args.cdxinject = os.path.join(args.output, f"waybackup_{helper.sanitize_filename(args.url)}.cdx")
+    else:
+        if args.skip is True:
+            args.skip = args.output
+        if args.csv is True:
+            args.csv = args.output
+        if args.cdxbackup is True:
+            args.cdxbackup = args.output
+        if args.cdxinject is True:
+            args.cdxinject = args.output
 
     if args.save:
         archive.save_page(args.url)

{pywaybackup-1.2.6 → pywaybackup-1.3.0/pywaybackup.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: pywaybackup
-Version: 1.2.6
+Version: 1.3.0
 Summary: Download snapshots from the Wayback Machine
 Home-page: https://github.com/bitdruid/python-wayback-machine-downloader
 Author: bitdruid
@@ -102,6 +102,10 @@ Path defaults to output-dir. Saves the result of CDX query as a file. Useful for
 - **`--cdxinject`** `<filepath>`:<br>
 Injects a CDX query file to download snapshots. Ensure the query matches the previous `--url` for correct folder structure.
 
+**Auto:**
+- **`--auto`**:<br>
+If set, csv, skip and cdxbackup/cdxinject are handled automatically. Keep the files and folders as they are. Otherwise they will not be recognized when restarting a download.
+
 ### Debug
 
 - `--debug`: If set, full traceback will be printed in case of an error. The full exception will be written into `waybackup_error.log`.

pywaybackup-1.2.6/pywaybackup/__version__.py

@@ -1 +0,0 @@
-__version__ = "1.2.6"