Merge pull request #187 from pukkandan/break-on-existing

Stop download after encountering video in archive

README.md

@@ -217,6 +217,8 @@ I will add some memorable short links to the binaries so you can download them e
     --download-archive FILE          Download only videos not listed in the
                                      archive file. Record the IDs of all
                                      downloaded videos in it.
+    --break-on-existing              Stop the download process after attempting
+                                     to download a file that's in the archive.
     --include-ads                    Download advertisements as well
                                      (experimental)
 

youtube_dlc/YoutubeDL.py

@@ -210,6 +210,8 @@ class YoutubeDL(object):
     download_archive:  File name of a file where all downloads are recorded.
                        Videos already present in the file are not downloaded
                        again.
+    break_on_existing: Stop the download process after attempting to download a file that's
+                       in the archive.
     cookiefile:        File name where cookies should be read from and dumped to.
     nocheckcertificate:Do not verify SSL certificates
     prefer_insecure:   Use HTTP instead of HTTPS to retrieve information.
@@ -821,12 +823,22 @@ class YoutubeDL(object):
             if not ie.suitable(url):
                 continue
 
-            ie = self.get_info_extractor(ie.ie_key())
+            ie_key = ie.ie_key()
+            ie = self.get_info_extractor(ie_key)
             if not ie.working():
                 self.report_warning('The program functionality for this site has been marked as broken, '
                                     'and will probably not work.')
 
             try:
+                try:
+                    temp_id = ie.extract_id(url) if callable(getattr(ie, 'extract_id', None)) else ie._match_id(url)
+                except (AssertionError, IndexError):
+                    temp_id = None
+                if temp_id is not None and self.in_download_archive({'id': temp_id, 'ie_key': ie_key}):
+                    self.to_screen("[%s] %s: has already been recorded in archive" % (
+                                   ie_key, temp_id))
+                    break
+
                 ie_result = ie.extract(url)
                 if ie_result is None:  # Finished already (backwards compatibility; listformats and friends should be moved here)
                     break
@@ -1038,8 +1050,12 @@ class YoutubeDL(object):
 
                 reason = self._match_entry(entry, incomplete=True)
                 if reason is not None:
-                    self.to_screen('[download] ' + reason)
-                    continue
+                    if reason.endswith('has already been recorded in the archive') and self.params.get('break_on_existing'):
+                        print('[download] tried downloading a file that\'s already in the archive, stopping since --break-on-existing is set.')
+                        break
+                    else:
+                        self.to_screen('[download] ' + reason)
+                        continue
 
                 entry_result = self.process_ie_result(entry,
                                                       download=download,

youtube_dlc/__init__.py

@@ -405,6 +405,7 @@ def _real_main(argv=None):
         'youtube_print_sig_code': opts.youtube_print_sig_code,
         'age_limit': opts.age_limit,
         'download_archive': download_archive_fn,
+        'break_on_existing': opts.break_on_existing,
         'cookiefile': opts.cookiefile,
         'nocheckcertificate': opts.no_check_certificate,
         'prefer_insecure': opts.prefer_insecure,

youtube_dlc/options.py

@@ -344,6 +344,10 @@ def parseOpts(overrideArguments=None):
         '--download-archive', metavar='FILE',
         dest='download_archive',
         help='Download only videos not listed in the archive file. Record the IDs of all downloaded videos in it.')
+    selection.add_option(
+        '--break-on-existing',
+        action='store_true', dest='break_on_existing', default=False,
+        help="Stop the download process after attempting to download a file that's in the archive.")
     selection.add_option(
         '--include-ads',
         dest='include_ads', action='store_true',