From 1f0b8be3756cc52f3c911735dbc15f4063e133d2 Mon Sep 17 00:00:00 2001
From: Bryan Newbold <bnewbold@archive.org>
Date: Wed, 22 Apr 2020 10:48:56 -0700
Subject: init repo with work-in-progress script

---
 .gitignore  |  21 ++++++++
 Pipfile     |  11 +++++
 README.md   |  37 ++++++++++++++
 example.env |   4 ++
 reupload.py | 157 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
 5 files changed, 230 insertions(+)
 create mode 100644 .gitignore
 create mode 100644 Pipfile
 create mode 100644 README.md
 create mode 100644 example.env
 create mode 100755 reupload.py

diff --git a/.gitignore b/.gitignore
new file mode 100644
index 0000000..81a4762
--- /dev/null
+++ b/.gitignore
@@ -0,0 +1,21 @@
+*.o
+*.a
+*.pyc
+#*#
+*~
+*.swp
+.*
+*.tmp
+*.old
+*.profile
+*.bkp
+*.bak
+[Tt]humbs.db
+*.DS_Store
+build/
+_build/
+src/build/
+*.log
+
+# Don't ignore this file itself
+!.gitignore
diff --git a/Pipfile b/Pipfile
new file mode 100644
index 0000000..219b717
--- /dev/null
+++ b/Pipfile
@@ -0,0 +1,11 @@
+[[source]]
+url = "https://pypi.python.org/simple"
+verify_ssl = true
+name = "pypi"
+
+[packages]
+
+[dev-packages]
+
+[requires]
+python_version = "3.7"
diff --git a/README.md b/README.md
new file mode 100644
index 0000000..7ba167d
--- /dev/null
+++ b/README.md
@@ -0,0 +1,37 @@
+
+Want to download all ELS instagram photos, with at least date metadata, then
+re-upload to wiki.mako.cc (or some other location).
+
+## Experimentation
+
+Using `pipenv` to generate a python virtualenv:
+
+    pipenv shell
+    pip install instaloader requests
+
+Then:
+
+    instaloader profile --no-compress-json extraordinaryleastsquares
+    # "Warning: Use --login to download HD version of profile pictures"
+
+In the future:
+
+    instaloader --fast-update --no-compress-json extraordinaryleastsquares
+
+For mediawiki API, docs describe using requests: <https://www.mediawiki.org/wiki/API:Images#Python>
+
+Metadata for items:
+
+    filename: CEQD_<date>_<time>_<imagenum>.jpg
+    summary:
+        <instagram_comment>
+        Imported from ELS instagram: https://www.instagram.com/p/<short_id>/
+
+    page:
+        [[Category:Center for Extraordinary Quarantine Dining]]
+
+        == Summary ==
+        veggie #katsudon from a couple nights ago, galangal #broccoli on the side
+
+        Imported from ELS instagram: https://www.instagram.com/p/B9r_0Fsl1eh/
+
diff --git a/example.env b/example.env
new file mode 100644
index 0000000..6be0480
--- /dev/null
+++ b/example.env
@@ -0,0 +1,4 @@
+# Copy this file to .env. pipenv will then detect it when you run things like
+# `pipenv shell` or `pipenv run`
+WIKI_USERNAME="CHANGEME"
+WIKI_PASSWORD="CHANGEME"
diff --git a/reupload.py b/reupload.py
new file mode 100755
index 0000000..94fbbe3
--- /dev/null
+++ b/reupload.py
@@ -0,0 +1,157 @@
+#!/usr/bin/env python3
+
+import os
+import sys
+import json
+from typing import Optional
+import requests
+import argparse
+
+BASE_URL = "https://wiki.mako.cc/api.php"
+
+
+def login(session: requests.Session) -> (str, str):
+
+    bot_username = os.environ['WIKI_USERNAME']
+    bot_password = os.environ['WIKI_PASSWORD']
+
+    # Step 1: Retrieve a login token
+    resp = session.get(
+        BASE_URL,
+        params={
+            "action": "query",
+            "meta": "tokens",
+            "type": "login",
+            "format": "json",
+        },
+    )
+
+    resp.raise_for_status()
+    login_token = resp.json()['query']['tokens']['logintoken']
+    assert login_token
+
+    # Step 2: Send a post request to login. Use of main account for login is not
+    # supported. Obtain credentials via Special:BotPasswords
+    # (https://www.mediawiki.org/wiki/Special:BotPasswords) for lgname & lgpassword
+    resp = session.post(
+        BASE_URL,
+        data={
+            "action": "login",
+            "lgname": bot_username,
+            "lgpassword": bot_password,
+            "format": "json",
+            "lgtoken": login_token, 
+        },
+    )
+
+    resp.raise_for_status()
+
+    # Step 3: While logged in, retrieve a CSRF token
+    resp = session.get(
+        BASE_URL,
+        params={
+            "action": "query",
+            "meta":"tokens",
+            "format":"json"
+        },
+    )
+
+    resp.raise_for_status()
+    csrf_token = resp.json()['query']['tokens']['csrftoken']
+    assert csrf_token
+
+    return (login_token, csrf_token)
+
+def get_imageinfo(title: str, session: requests.Session) -> Optional[dict]:
+    """Returns a dict, or None if image not found"""
+
+    assert not title.startswith("File:")
+    # Does not require authentication
+    resp = session.get(
+        BASE_URL,
+        params={
+            "action": "query",
+            "format": "json",
+            "prop": "imageinfo",
+            "titles": f"File:{title}"
+        },
+    )
+    resp.raise_for_status()
+    pages = resp.json()['query']['pages']
+    if "-1" in pages:
+        return None
+    else:
+        return list(pages.values())[0]
+
+def reupload_post(args):
+
+    # parse metadata
+    base_path = args.json_file.replace('.json', '')
+    meta = json.loads(open(args.json_file, 'r').read())['node']
+    #print(meta)
+    shortcode = meta['shortcode']
+    caption = meta['edge_media_to_caption']['edges'][0]['node']['text']
+
+    if meta.get('edge_sidecar_to_children'):
+        image_count = len(meta['edge_sidecar_to_children']['edges'])
+    else:
+        image_count = 1
+
+    if image_count != 1:
+        raise NotImplementedError()
+
+    jpeg_path = base_path + ".jpg"
+    date_part = base_path.split('/')[1].split('_')[0].replace('-', '')
+    time_part = base_path.split('/')[1].split('_')[1].replace('-', '')[:4]
+    remote_name = f"CEQD_{date_part}_{time_part}_1.jpg"
+    page_text = f"""[[Category:Center for Extraordinary Quarantine Dining]]
+
+== Summary ==
+{caption}
+
+Imported from ELS instagram: https://www.instagram.com/p/{shortcode}/
+    """
+
+    session = requests.Session()
+    (login_token, csrf_token) = login(session)
+
+    # First, check if file already exists
+    existing = get_imageinfo(remote_name, session)
+    if existing:
+        print(json.dumps(existing, sort_keys=True, indent=2))
+        sys.exit(-1)
+
+    # If it doesn't, upload it!
+    print(f"Uploading {remote_name}")
+    resp = session.post(
+        BASE_URL,
+        data={
+            "action": "upload",
+            "filename": remote_name,
+            "text": page_text,
+            "format": "json",
+            "token": csrf_token,
+            "ignorewarnings": 1
+        },
+        files={
+            'file': ('filename.jpg', open(jpeg_path, 'rb'), 'multipart/form-data'),
+        },
+    )
+    resp.raise_for_status()
+    print(json.dumps(resp.json(), sort_keys=True, indent=2)
+
+def main():
+    parser = argparse.ArgumentParser(
+        formatter_class=argparse.ArgumentDefaultsHelpFormatter)
+    parser.add_argument(
+        'json_file',
+        help="JSON metadata file",
+        type=str,
+        #type=argparse.FileType('r'),
+    )
+    args = parser.parse_args()
+
+    reupload_post(args)
+
+if __name__ == "__main__":
+    main()
-- 
cgit v1.2.3