From ae6c39c8e9758172c92136128c811f2387531228 Mon Sep 17 00:00:00 2001 From: Jan Tuomi Date: Tue, 2 Feb 2021 21:28:12 +0200 Subject: Rename to kanji_info_fetcher --- attain_vocab_to_anki_py/wadoku_client.py | 42 -------------------------------- 1 file changed, 42 deletions(-) delete mode 100644 attain_vocab_to_anki_py/wadoku_client.py (limited to 'attain_vocab_to_anki_py/wadoku_client.py') diff --git a/attain_vocab_to_anki_py/wadoku_client.py b/attain_vocab_to_anki_py/wadoku_client.py deleted file mode 100644 index 550f801..0000000 --- a/attain_vocab_to_anki_py/wadoku_client.py +++ /dev/null @@ -1,42 +0,0 @@ -from bs4 import BeautifulSoup -import requests -import urllib.parse - -WADOKU_BASE_URL = "https://www.wadoku.de/search" - -def inject_hiragana_with_accents(entries: list) -> list: - entries_with_readings = [] - - for index, entry in enumerate(entries): - kanji = entry.kanji.replace("~", "") - - if len(entry.hiragana) > 0: - print(f"Hiragana exists for #{index}: {kanji}. Skipping...") - entries_with_readings.append(entry) - continue - - # Remove nasty characters from kanji since Wadoku - # fails to find anything otherwise - print(f"Fetching hiragana data for #{index}: {kanji}") - - resource_part = urllib.parse.quote_plus(kanji) - url = f"{WADOKU_BASE_URL}/{resource_part}" - resp = requests.get(url) - resp.raise_for_status() - - soup = BeautifulSoup(resp.text, "html.parser") - container = soup.select_one("section#content") - - readings = container.select("span.reading") - first_reading = str(readings[0]) - - # Remove extra characters added by Wadoku - # https://www.wadoku.de/wiki/display/WAD/Hinweise+zur+Notation - result = first_reading \ - .replace("~", "") \ - .replace("|", "") \ - .replace("・", "") - entry.hiragana = result - entries_with_readings.append(entry) - - return entries_with_readings -- cgit v1.3