def parseDataFromIndiWords(data):
declesions = []
for word, url in data:
domain = "https://en.wiktionary.org%s"
page = utils.fetchSoup(domain % url)
try:
table = page("table", {"class" : "prettytable"})[0]
# print(str(table)[30:50])
nouns = [unicode(i.string) for i in page("ol")[0]("a")]
print(nouns)
gender = unicode(page("span", {"class" : "gender"})[0].string)
print(gender)
except:
print("[+] Table for word : %s not found!" % word)
table, nouns = [], []
# processing begins here
try:
tableProcd = [[unicode(k.string) for k in j("td")] for j in table("tr")]
print("[+] Word %s has %d nouns" % (word, len(nouns)))
declesions.append((word, nouns, tableProcd, gender))
except Exception as e:
print(e)
print("[!] Seems like there exists No required Data, SKIP!")
utils.sleeper(3)
# break
return declesions
#!/usr/bin/env python
import utils
import parser
data = []
url = "https://en.wiktionary.org/wiki/Category:Faroese_nouns"
while True:
# fetching and creating soup
soup = utils.fetchSoup(url)
# div housing the words
page = soup("div", {"id": "mw-pages"})
# word groups
groups = page[0]("div", {"class": "mw-category-group"})
# traverse of very group and extract data into groupD
for g in groups:
words = [(unicode(i("a")[0].string), i("a")[0]["href"]) for i in g("li")]
categ = unicode(g("h3")[0].string)
data.extend(words)
print ("[*] Letter %s has %d words" % (categ, len(words)))
# extract url for next page
links = page[0]("a")
nextL = [x for x in links if x.string == "next page"]
if len(nextL) == 0:
print ("Done Scraping!")