From b43cd881015bdd4cb5c990281332f6c87cc0f63a Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Mike=20F=C3=A4hrmann?= <mike_faehrmann@web.de>
Date: Wed, 12 Apr 2017 18:43:41 +0200
Subject: [PATCH] add '-j/--dump-json' option

this outputs the extractor-results in JSON format rather then
downloading files
---
 gallery_dl/__init__.py |  2 ++
 gallery_dl/job.py      | 35 ++++++++++++++++++++++++++++++++++-
 gallery_dl/option.py   |  4 ++++
 3 files changed, 40 insertions(+), 1 deletion(-)

diff --git a/gallery_dl/__init__.py b/gallery_dl/__init__.py
index e3785d34..71715ae5 100644
--- a/gallery_dl/__init__.py
+++ b/gallery_dl/__init__.py
@@ -83,6 +83,8 @@ def main():
                 jobtype.maxdepth = args.list_urls
             elif args.list_keywords:
                 jobtype = job.KeywordJob
+            elif args.list_data:
+                jobtype = job.DataJob
             else:
                 jobtype = job.DownloadJob
 
diff --git a/gallery_dl/job.py b/gallery_dl/job.py
index 41da2ae7..7453305c 100644
--- a/gallery_dl/job.py
+++ b/gallery_dl/job.py
@@ -6,6 +6,7 @@
 # it under the terms of the GNU General Public License version 2 as
 # published by the Free Software Foundation.
 
+import sys
 import json
 import hashlib
 from . import extractor, downloader, config, util, output, exception
@@ -79,7 +80,7 @@ class Job():
                 )
             # TODO: support for multiple message versions
 
-    def handle_url(self, url, kexwords):
+    def handle_url(self, url, keywords):
         """Handle Message.Url"""
 
     def handle_directory(self, keywords):
@@ -265,3 +266,35 @@ class TestJob(DownloadJob):
         """Update the content hash"""
         if self.content:
             self.get_downloader(url).download(url, self.fileobj)
+
+
+class DataJob(Job):
+    """Collect extractor results and dump them"""
+
+    def __init__(self, url, file=sys.stdout):
+        Job.__init__(self, url)
+        self.file = file
+        self.data = []
+        self.ensure_ascii = config.get(("output", "ascii"), True)
+
+    def run(self):
+        # collect data
+        try:
+            for msg in self.extractor:
+                if msg[0] in (Message.Headers, Message.Cookies):
+                    copy = (msg[0], dict(msg[1]))
+                else:
+                    copy = [
+                        part.copy() if hasattr(part, "copy") else part
+                        for part in msg
+                ]
+                self.data.append(copy)
+        except Exception as exc:
+            self.data.append((exc.__class__.__name__, str(exc)))
+
+        # dump to 'file'
+        json.dump(
+            self.data, self.file,
+            sort_keys=True, indent=2, ensure_ascii=self.ensure_ascii
+        )
+        self.file.write("\n")
diff --git a/gallery_dl/option.py b/gallery_dl/option.py
index 5f40d953..9a87c9ad 100644
--- a/gallery_dl/option.py
+++ b/gallery_dl/option.py
@@ -63,6 +63,10 @@ def build_parser():
         "-g", "--get-urls", dest="list_urls", action="count",
         help="Print download urls",
     )
+    parser.add_argument(
+        "-j", "--dump-json", dest="list_data", action="store_true",
+        help="Print JSON information",
+    )
     parser.add_argument(
         "-d", "--dest",
         metavar="DEST", action=ConfigAction, dest="base-directory",