Rename to kanji_info_fetcher

1 files changed, 92 insertions, 0 deletions

diff --git a/kanji_info_fetcher/jisho_client.py b/kanji_info_fetcher/jisho_client.py
new file mode 100644
index 0000000..e74412e
--- /dev/null
+++ b/kanji_info_fetcher/jisho_client.py
@@ -0,0 +1,92 @@
+from bs4 import BeautifulSoup
+import requests
+import urllib.parse
+
+JISHO_BASE_URL = "https://jisho.org/search"
+
+def _meaning_tag_to_abbrev(tag: str) -> str:
+  if "Godan" in tag: return "G1"
+  if "Ichidan" in tag: return "G2"
+  if "Suru" in tag: return "G3"
+  if "Noun" in tag: return "n."
+  if "I-adjective" in tag: return "い-adj."
+  if "Na-adjective" in tag: return "な-adj."
+  if "No-adjective" in tag: return "の-adj."
+  if "Adverb" in tag: return "adv."
+  return tag
+
+def inject_kanji_meanings(entries: list) -> list:
+  entries_with_meanings = []
+
+  for index, entry in enumerate(entries):
+    kanji = entry.kanji
+
+    if len(entry.meanings) > 0:
+      print(f"Meaning data exists for #{index}: {kanji}. Skipping...")
+      entries_with_meanings.append(entry)
+      continue
+
+    print(f"Fetching meaning data from Jisho 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
+
+def inject_english_translation(entries: list) -> list:
+  entries_with_translations = []
+
+  for index, entry in enumerate(entries):
+    kanji = entry.kanji
+
+    if len(entry.english) > 0:
+      print(f"English translation exists for #{index}: {kanji}. Skipping...")
+      entries_with_translations.append(entry)
+      continue
+
+    print(f"Fetching translation from Jisho for #{index}: {kanji}")
+
+    resource_part = urllib.parse.quote_plus(f"{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")
+
+    meaning_wrapper = container.select(".meanings-wrapper")[0]
+
+    meaning_tags = meaning_wrapper.select(".meaning-tags")
+    meaning_tags_texts = map(lambda e: e.text.strip(), meaning_tags)
+    meaning_tag_abbrevs = map(_meaning_tag_to_abbrev, meaning_tags_texts)
+
+    meaning_translations = meaning_wrapper.select(".meaning-wrapper .meaning-meaning")
+    meaning_translations_texts = map(lambda e: e.text.strip(), meaning_translations)
+
+    meanings_zipped = zip(meaning_tag_abbrevs, meaning_translations_texts)
+
+    first_translation_pair = list(meanings_zipped)[0]
+    result = f"{first_translation_pair[0]} {first_translation_pair[1]}"
+
+    entry.english = result
+    entries_with_translations.append(entry)
+
+  return entries_with_translations