dict_generator.py

#!/usr/bin/env python3
#
# Usage example:
#
#   echo "hello\nworld" > words.txt
#   ./dict_generator.py > dict.md
#   pandoc -s dict.md -o dict.doc
#
import bs4
import time
import requests


INPUT_FNAME = "words.txt"


def yandex_translate(word):
    data = {
        "text": word,
        "format": "plain",
        "lang": "en-ru",
        # Stolen from: https://github.com/dveselov/python-yandex-translate/blob/master/yandex_translate/__init__.py
        "key": "trnsl.1.1.20130421T140201Z.323e508a33e9d84b.f1e0d9ca9bcd0a00b0ef71d82e6cf4158183d09e"}
    response = requests.post("https://translate.yandex.net/api/v1.5/tr.json/translate", params=data, proxies=None)
    return response.json().get("text")[0]


def oxford(word, session):
    if word and session:
        u = f"https://en.oxforddictionaries.com/search?filter=dictionary&query={word}"
        headers = {
            "Accept" : "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8",
            "X-Requested-With": "XMLHttpRequest",
            "Referer": "https://en.oxforddictionaries.com/",
            "Host": "en.oxforddictionaries.com"}
        response = session.get(u, headers=headers, allow_redirects=True)
        soup = bs4.BeautifulSoup(response.text, "html.parser")

        try:
            pron = soup.find("span", class_="phoneticspelling").get_text()
            pron = f"*{pron}*"  # italic
        except:
            pron = ''
        try:
            meaning = soup.find("span", class_="ind").get_text()
        except:
            meaning = ''
        try:
            example = soup.find("div", {"class": "ex"}).get_text()
            example = example[2].upper() + example[3:len(example)-1] + '.'
        except:
            example = ''
        try:
            synonym = soup.find("div", {"class": "exs"}).get_text()
        except:
            synonym = ''

        if "Retry" in response.text[0:30]:
            time.sleep(5)

        return f" {pron} | {meaning} | {synonym} | {example} "

    return None


if __name__ == "__main__":
    words = []
    with open(INPUT_FNAME) as f:
        words = [line.split()[0] for line in f]

    s = requests.Session()
    s.headers = {"User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/55.0.2883.95 Safari/537.36"}
    s.get("https://en.oxforddictionaries.com/")

    print("№ | Word | Translation | Pronounce | Meaning | Synonyms | Example ")
    print("--|------|-------------|-----------|---------|----------|---------")
    for i, w in enumerate(words):
        print(f"{i+1} | {w} | {yandex_translate(w)} | {oxford(w, s)} |")

# vim:foldmethod=marker:foldenable:tw=120