From 17da3fbdeb2f53de0d04cac8d14910dc89b96d0b Mon Sep 17 00:00:00 2001
From: Luca Beltrame <lbeltrame@kde.org>
Date: Thu, 3 Jan 2019 12:49:53 +0100
Subject: [PATCH] Convert nico comments

---
 nico_comment.py | 83 +++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 83 insertions(+)
 create mode 100755 nico_comment.py

diff --git a/nico_comment.py b/nico_comment.py
new file mode 100755
index 0000000..34b4b1d
--- /dev/null
+++ b/nico_comment.py
@@ -0,0 +1,83 @@
+#!/usr/bin/python3
+
+import asyncio
+import argparse
+from datetime import datetime
+import netrc
+import os
+from urllib.parse import urlparse
+
+import pandas as pd
+from nicotools.download import Comment, Info, utils
+import simplejson as json
+
+
+def process_element(element):
+
+    element = element["chat"]
+
+    video_pos = element["vpos"] * 10
+    comment = element["content"]
+    video_time = datetime.fromtimestamp(video_pos / 1000).strftime("%M:%S.%f")
+
+    return (video_time, comment)
+
+
+def extract_ids(urls):
+
+    video_ids = list()
+
+    for url in urls:
+        parsed = urlparse(url)
+        nico_id = os.path.split(parsed.path)[-1]
+        video_ids.append(nico_id)
+
+    return nico_id
+
+
+class CommentStream(Comment):
+
+    def saver(self, video_id: str, is_xml: bool,
+              coroutine: asyncio.Task) -> bool:
+        comment_data = coroutine.result()
+        conts = list()
+
+        if not is_xml:
+            data = json.loads(comment_data)
+            contents = [process_element(item)
+                        for item in data if "chat" in item]
+
+            file_path = utils.make_name(self.glossary[video_id], "",
+                                        extention="txt")
+
+            df = pd.DataFrame.from_records(contents,
+                                           columns=["Time", "Comment"])
+            df["Time"] = pd.to_datetime(df["Time"],
+                                        format="%M:%S.%f").dt.time
+            df = df.sort_values(by="Time")
+
+
+            with file_path.open("w", encoding="utf-8") as f:
+                df.to_csv(f, sep="\t", index=False)
+
+        return True
+
+
+def main():
+
+    parser = argparse.ArgumentParser()
+    parser.add_argument("video", help="Video URL(s)", nargs="+")
+    parser.add_argument("-d", "--destination", help="Destination directory",
+                        default="./")
+
+    options = parser.parse_args()
+    user, _, password = netrc.netrc().hosts["niconico"]
+    video_ids = extract_ids(options.video)
+
+    database = Info(video_ids, mail=user, password=password).info
+    com = CommentStream(database, user, password, save_dir=options.destination)
+    com.start()
+
+
+if __name__ == "__main__":
+    main()