def extracts(lang, titles, limit):
wc = WapitiClient('*****@*****.**',
api_url='https://' + lang + '.wikipedia.org/w/api.php')
if limit > len(titles):
limit = len(titles)
ret = {}
for i in range(limit):
title = titles[i]
res = wc.get_page_extract(title)
if res:
ret[title] = {'title': title, 'extract': res[0].extract}
return ret
def extracts(lang, titles, limit):
wc = WapitiClient('*****@*****.**',
api_url='https://' + lang + '.wikipedia.org/w/api.php')
if limit > len(titles):
limit = len(titles)
ret = {}
for i in range(limit):
title = titles[i]
res = wc.get_page_extract(title)
if res:
ret[title] = {'title': title, 'extract': res[0].extract}
return ret
from wapiti import WapitiClient
client = WapitiClient('*****@*****.**')
res = []
cats = ('Africa', 'FA-Class_articles', 'GA-Class_articles', 'Physics')
for cat in cats:
res.append(client.get_category_recursive(cat, 1000))
print res[0][0]
import pdb;pdb.set_trace()
# -*- coding: utf-8 -*-
# <nbformat>3</nbformat>
# <codecell>
from wapiti import WapitiClient
from pprint import pprint as pp
client = WapitiClient('*****@*****.**')
# <codecell>
client.get_ancient_pages(limit=5)
# <codecell>
client.get_category_articles('Africa', limit=5)
# <codecell>
es_client = WapitiClient('*****@*****.**', api_url='http://es.wikipedia.org/w/api.php')
# a handy mapping of namespace name translations
dict([(x.canonical, x.title) for x in es_client.source_info.namespace_map])
# <codecell>
client.print_usage()
# -*- coding: utf-8 -*-
# <nbformat>3</nbformat>
# <codecell>
from wapiti import WapitiClient
from pprint import pprint as pp
client = WapitiClient('*****@*****.**')
# <codecell>
client.get_ancient_pages(limit=5)
# <codecell>
client.get_category_articles('Africa', limit=5)
# <codecell>
es_client = WapitiClient('*****@*****.**',
api_url='http://es.wikipedia.org/w/api.php')
# a handy mapping of namespace name translations
dict([(x.canonical, x.title) for x in es_client.source_info.namespace_map])
# <codecell>
client.print_usage()
import gevent
from gevent import monkey
monkey.patch_all()
from wapiti import WapitiClient
client = WapitiClient('*****@*****.**')
cats = ('Africa', 'FA-Class_articles', 'GA-Class_articles', 'Physics')
tasks = [gevent.spawn(client.get_category_recursive, x, 1000) for x in cats]
gevent.wait(tasks)
print tasks[0].value[0]
import pdb
pdb.set_trace()
which results in a list of lists like this:
[u'English', u'w:English language', u'en', u'4,234,378', u'129,657', u'763']
"""
import os
import sys
import json
import re
from pyquery import PyQuery
from wapiti import WapitiClient
wikis_json_filename = sys.argv[1]
wikis_json = open(wikis_json_filename, 'rb').read()
wikis_list = json.loads(wikis_json)
wc = WapitiClient('*****@*****.**')
RE_INTRO = re.compile(r'(?P<intro>.*?\.)\s*([A-Z\[\n]{1}|\Z)')
RE_FN = re.compile(r'\[[0-9]{1,2}\]')
def parse_count(count_text):
try:
return int(count_text.replace(',', '').strip())
except AttributeError:
raise
def get_desc(article_name):
lang_article = wc.web_request_operation('http://en.wikipedia.org/wiki/' +
article_name)
pq = PyQuery(lang_article[0])
