Added option --break-on-reject

and modified `--break-on-existing`

README.md

@@ -250,8 +250,10 @@ ## Video Selection:
     --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
+    --break-on-existing              Stop the download process when encountering
-                                     to download a file that's in the archive.
+                                     a file that's in the archive.
+    --break-on-reject                Stop the download process when encountering
+                                     a file that has been filtered out.
     --no-download-archive            Do not use archive file (default)
     --include-ads                    Download advertisements as well
                                      (experimental)

youtube_dlc/YoutubeDL.py

@@ -58,6 +58,7 @@
     encode_compat_str,
     encodeFilename,
     error_to_compat_str,
+    ExistingVideoReached,
     expand_path,
     ExtractorError,
     format_bytes,
@@ -81,6 +82,7 @@
     register_socks_protocols,
     render_table,
     replace_extension,
+    RejectedVideoReached,
     SameFileError,
     sanitize_filename,
     sanitize_path,
@@ -232,6 +234,7 @@ class YoutubeDL(object):
                        again.
     break_on_existing: Stop the download process after attempting to download a file that's
                        in the archive.
+    break_on_reject:   Stop the download process when encountering a video that has been filtered out.
     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.
@@ -797,6 +800,7 @@ def prepare_filename(self, info_dict):
     def _match_entry(self, info_dict, incomplete):
         """ Returns None if the file should be downloaded """
 
+        def check_filter():
             video_title = info_dict.get('title', info_dict.get('id', 'video'))
             if 'title' in info_dict:
                 # This can happen when we're just evaluating the playlist
@@ -833,9 +837,17 @@ def _match_entry(self, info_dict, incomplete):
                     ret = match_filter(info_dict)
                     if ret is not None:
                         return ret
-
             return None
 
+        reason = check_filter()
+        if reason is not None:
+            self.to_screen('[download] ' + reason)
+            if reason.endswith('has already been recorded in the archive') and self.params.get('break_on_existing'):
+                raise ExistingVideoReached()
+            elif self.params.get('break_on_reject'):
+                raise RejectedVideoReached()
+        return reason
+
     @staticmethod
     def add_extra_info(info_dict, extra_info):
         '''Set the keys from extra_info in info dict if they are missing'''
@@ -895,7 +907,7 @@ def wrapper(self, *args, **kwargs):
                 self.report_error(msg)
             except ExtractorError as e:  # An error we somewhat expected
                 self.report_error(compat_str(e), e.format_traceback())
-            except MaxDownloadsReached:
+            except (MaxDownloadsReached, ExistingVideoReached, RejectedVideoReached):
                 raise
             except Exception as e:
                 if self.params.get('ignoreerrors', False):
@@ -1098,14 +1110,7 @@ def report_download(num_entries):
                     'extractor_key': ie_result['extractor_key'],
                 }
 
-                reason = self._match_entry(entry, incomplete=True)
+                self._match_entry(entry, incomplete=True)
-                if reason is not None:
-                    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_iterable_entry(entry, download, extra)
                 # TODO: skip failed (empty) entries?
@@ -1870,9 +1875,7 @@ def process_info(self, info_dict):
         if 'format' not in info_dict:
             info_dict['format'] = info_dict['ext']
 
-        reason = self._match_entry(info_dict, incomplete=False)
+        if self._match_entry(info_dict, incomplete=False) is not None:
-        if reason is not None:
-            self.to_screen('[download] ' + reason)
             return
 
         self._num_downloads += 1
@@ -2260,7 +2263,13 @@ def download(self, url_list):
             except UnavailableVideoError:
                 self.report_error('unable to download video')
             except MaxDownloadsReached:
-                self.to_screen('[info] Maximum number of downloaded files reached.')
+                self.to_screen('[info] Maximum number of downloaded files reached')
+                raise
+            except ExistingVideoReached:
+                self.to_screen('[info] Encountered a file that did not match filter, stopping due to --break-on-reject')
+                raise
+            except RejectedVideoReached:
+                self.to_screen('[info] Encountered a file that is already in the archive, stopping due to --break-on-existing')
                 raise
             else:
                 if self.params.get('dump_single_json', False):

youtube_dlc/__init__.py

@@ -26,11 +26,13 @@
     decodeOption,
     DEFAULT_OUTTMPL,
     DownloadError,
+    ExistingVideoReached,
     expand_path,
     match_filter_func,
     MaxDownloadsReached,
     preferredencoding,
     read_batch_urls,
+    RejectedVideoReached,
     SameFileError,
     setproctitle,
     std_headers,
@@ -449,6 +451,7 @@ def parse_retries(retries):
         'age_limit': opts.age_limit,
         'download_archive': download_archive_fn,
         'break_on_existing': opts.break_on_existing,
+        'break_on_reject': opts.break_on_reject,
         'cookiefile': opts.cookiefile,
         'nocheckcertificate': opts.no_check_certificate,
         'prefer_insecure': opts.prefer_insecure,
@@ -519,8 +522,8 @@ def parse_retries(retries):
                 retcode = ydl.download_with_info_file(expand_path(opts.load_info_filename))
             else:
                 retcode = ydl.download(all_urls)
-        except MaxDownloadsReached:
+        except (MaxDownloadsReached, ExistingVideoReached, RejectedVideoReached):
-            ydl.to_screen('--max-download limit reached, aborting.')
+            ydl.to_screen('Aborting remaining downloads')
             retcode = 101
 
     sys.exit(retcode)

youtube_dlc/options.py

@@ -367,7 +367,11 @@ def _comma_separated_values_options_callback(option, opt_str, value, parser):
     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.")
+        help="Stop the download process when encountering a file that's in the archive.")
+    selection.add_option(
+        '--break-on-reject',
+        action='store_true', dest='break_on_reject', default=False,
+        help="Stop the download process when encountering a file that has been filtered out.")
     selection.add_option(
         '--no-download-archive',
         dest='download_archive', action="store_const", const=None,

youtube_dlc/utils.py

@@ -2433,6 +2433,16 @@ def __init__(self, msg):
         self.msg = msg
 
 
+class ExistingVideoReached(YoutubeDLError):
+    """ --max-downloads limit has been reached. """
+    pass
+
+
+class RejectedVideoReached(YoutubeDLError):
+    """ --max-downloads limit has been reached. """
+    pass
+
+
 class MaxDownloadsReached(YoutubeDLError):
     """ --max-downloads limit has been reached. """
     pass