author |
Steve Losh <steve@stevelosh.com> |
date |
Fri, 15 Jul 2016 13:17:16 +0000 |
parents |
c68485e8d84b |
children |
(none) |
#!/Users/sjl/.virtualenvs/webscraping/bin/python3
import sys
import requests
from bs4 import BeautifulSoup
en_url = 'http://conjugator.reverso.net/conjugation-english-verb-%s.html'
is_url = 'http://www.verbix.com/webverbix/go.php?T1=%s&Submit=Go&D1=28&H1=128'
def english(word):
resp = requests.get(en_url % word).text
soup = BeautifulSoup(resp, "html.parser")
ws = [t.text.strip()
for t in soup.find_all(class_="indicative-wrap")[0]
.div
.find_all("i")[1:]]
ws[8] = "y'all"
# fix third person singular
v = ws[5]
ws[4:6] = ['he', v, 'she', v, 'it', v]
# fix third person plural
v = ws[15]
ws[14:15] = ['they ♂', v, 'they ♀', v, 'they ∅', v]
vals = [a + ' ' + b for a, b in zip(ws[::2], ws[1::2])]
return vals
def icelandic(word):
resp = requests.get(is_url % word).text
soup = BeautifulSoup(resp, "html.parser")
ws = [t.text.strip()
for t in soup.find_all(class_='pure-u-1-2')[0]
.find_all('span')]
# fix third person singular
v = ws[5]
ws[4:6] = ['hann', v, 'hún', v, 'það', v]
v = ws[15]
ws[14:15] = ['þeir', v, 'þær', v, 'þau', v]
vals = [a + ' ' + b for a, b in zip(ws[::2], ws[1::2])]
return vals
eng_word = sys.argv[1]
ice_word = sys.argv[2]
print('to %s\tað %s' % (eng_word, ice_word))
eng = english(eng_word)
ice = icelandic(ice_word)
for e, i in zip(eng, ice):
print('%s\t%s' % (e, i))
print('to %s / að %s\t' % (eng_word, ice_word), end='')
print('<table>', end='')
for e, i in zip(eng, ice):
e1, e2 = e.rsplit(' ', 1)
i1, i2 = i.split(' ')
print('<tr>', end='')
print('<td>%s</td><td>%s</td><td>%s</td><td><b>%s</b></td>' % (e1, e2, i1, i2), end='')
print('</tr>', end='')
print('</table>')