3 files changed, 99 insertions, 0 deletions
diff --git a/attain_vocab_to_anki_py/__init__.py b/attain_vocab_to_anki_py/__init__.py
new file mode 100644
index 0000000..dee97d6
--- /dev/null
+++ b/attain_vocab_to_anki_py/__init__.py
@@ -0,0 +1,26 @@
+import argparse
+import attain_vocab_to_anki_py.io
+import attain_vocab_to_anki_py.jisho_client
+
+__version__ = '0.1.0'
+
+def main():
+  parser = argparse.ArgumentParser(description='Convert course vocab into Anki deck')
+  parser.add_argument('file', metavar='file', type=str,
+                      help='vocabulary file path')
+
+  args = parser.parse_args()
+  file_path = args.file
+
+  # read entries from file
+  print(f"[STATUS] Reading file {file_path}")
+  entries = io.read_from_file(file_path)
+
+  # fetch kanji meanings from Jisho
+  print(f"[STATUS] Fetching kanji data from Jisho")
+  entries_with_meanings = jisho_client.inject_kanji_meanings(entries)
+
+  # write entries to file
+  out_file_name = f"{file_path}.out"
+  print(f"[STATUS] Writing result to file {out_file_name}")
+  io.write_to_file(out_file_name, entries_with_meanings)
diff --git a/attain_vocab_to_anki_py/io.py b/attain_vocab_to_anki_py/io.py
new file mode 100644
index 0000000..4288e06
--- /dev/null
+++ b/attain_vocab_to_anki_py/io.py
@@ -0,0 +1,38 @@
+from os import path
+from dataclasses import dataclass
+
+@dataclass
+class Entry:
+  kanji: str
+  hiragana: str
+  english: str
+  meanings: str
+
+def read_from_file(path_str: str) -> list:
+  p = path.join(path_str)
+  lines = []
+
+  with open(p, "r") as f:
+    lines = f.readlines()
+
+  entries = []
+  for line in lines:
+    kanji, hiragana, english = line.split(",", 2)
+    entries.append(Entry(kanji=kanji.strip(),
+      hiragana=hiragana.strip(),
+      english=english.strip(),
+      meanings=""))
+
+  return entries
+
+def _entry_to_row(entry: Entry, delimiter: str = ";") -> str:
+  s = delimiter.join([entry.kanji, entry.hiragana, entry.english, entry.meanings])
+  return f"{s}\n"
+
+def write_to_file(path_str: str, entries: list):
+  p = path.join(path_str)
+
+  lines = map(_entry_to_row, entries)
+
+  with open(p, "w") as f:
+    f.writelines(lines)
diff --git a/attain_vocab_to_anki_py/jisho_client.py b/attain_vocab_to_anki_py/jisho_client.py
new file mode 100644
index 0000000..0ca2147
--- /dev/null
+++ b/attain_vocab_to_anki_py/jisho_client.py
@@ -0,0 +1,35 @@
+from bs4 import BeautifulSoup
+import requests
+import urllib.parse
+
+JISHO_BASE_URL = "https://jisho.org/search"
+
+def inject_kanji_meanings(entries: list) -> list:
+  entries_with_meanings = []
+
+  for index, entry in enumerate(entries):
+    kanji = entry.kanji
+    print(f"Fetching data for #{index}: {kanji}")
+
+    resource_part = urllib.parse.quote_plus(f"{kanji}#kanji")
+    url = f"{JISHO_BASE_URL}/{resource_part}"
+    resp = requests.get(url)
+    resp.raise_for_status()
+
+    soup = BeautifulSoup(resp.text, "html.parser")
+    container = soup.select_one("div#page_container")
+
+    meanings = container.select(".kanji-details__main-meanings")
+    kanji_meaning_texts = map(lambda e: e.text.strip(), meanings)
+
+    kanji_characters = container.select(".character")
+    kanji_character_texts = map(lambda e: e.text.strip(), kanji_characters)
+
+    result_tuples = zip(kanji_character_texts, kanji_meaning_texts)
+    result_strs = map(lambda t: " ".join(t), result_tuples)
+    result = "<br>".join(result_strs)
+
+    entry.meanings = result
+    entries_with_meanings.append(entry)
+
+  return entries_with_meanings
+\ No newline at end of file