Last active
October 27, 2020 14:53
-
-
Save niyumard/eed1799119bb3022604322cefdc39489 to your computer and use it in GitHub Desktop.
This script looks up esperanto words in Lernu.net website, this script is specially made for being used via GoldenDict. Usage: >python lernulookup.py %GDWORD%
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/python | |
import requests,re, sys | |
from bs4 import BeautifulSoup | |
URL = 'https://lernu.net/en/vortaro' | |
client = requests.session() | |
# Retrieve the CSRF token first | |
z = client.get(URL) # sets cookie | |
if 'YII_CSRF_TOKEN' in client.cookies and 'PHPSESSID' in client.cookies: | |
#csrftoken = client.cookies['YII_CSRF_TOKEN'] | |
match = re.search(r"csrfToken: '(.*?)'", z.text) | |
csrftoken = match.group(1) | |
phpsessid = client.cookies['PHPSESSID'] | |
else: | |
print("Seesion Failure") | |
cookiee = "PHPSESSID=" + phpsessid + "; YII_CSRF_TOKEN=" + csrftoken + "; lang=en" | |
header = { | |
'Accept':'*/*', | |
"Accept-Encoding": "gzip, deflate, br", | |
'Accept-Language': 'en-US,en;q=0.5', | |
'Connection': 'keep-alive', | |
'Content-Type':'application/x-www-form-urlencoded; charset=UTF-8', | |
'Cookie': cookiee, | |
'DNT':'1', | |
'Host':'lernu.net', | |
'Origin':'https://lernu.net', | |
'Sec-GPC':'1', | |
'Referer': URL, | |
"User-Agent":"Mozilla/5.0 (X11; Linux x86_64; rv:78.0) Gecko/20100101 Firefox/78.0", | |
'X-Requested-With':'XMLHttpRequest' | |
} | |
cookiee_in_request = { | |
'lang': 'en', | |
'PHPSESSID': phpsessid, | |
'YII_CSRF_TOKEN': csrftoken | |
} | |
listoflangs = ["eo|fr","eo|en","eo|fa"] | |
for i in listoflangs: | |
login_data = {"YII_CSRF_TOKEN":csrftoken, 'DictWords[word]': sys.argv[1], "DictWords[dictionary]": i} | |
try: | |
r = client.post(URL, data=login_data, headers=header, cookies=cookiee_in_request) | |
if r.status_code == 200: | |
pass | |
else: | |
print("Failed connecting to the server.") | |
soup = BeautifulSoup(r.text, 'html.parser') | |
if 'class="empty"' not in str(soup.find(id="dictionary-search-results").findAll('ul')): | |
print(soup.find(id="dictionary-search-results").findAll('ul')[0]) | |
else: | |
print("Erorr parsing website text.") | |
except: | |
print("Failed.") |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment