def main():
"""Print Wiktionary engine JSON to STDOUT."""
data = mkdata('Wiktionary', 'Collaborative dictionary', pcencode=True)
soup = BS(html(), 'html.parser')
# Use 'langlist-large' css class for wiktionaries with
# 10K+ entries.
# Class 'langlist' will get wikitionaries with 100+ entries.
for div in soup.find_all('div', class_='langlist-large'):
for link in div.select('ul li a'):
# log('link=%r', link)
lang = id_ = link['lang']
url = 'https:' + link['href']
name = link.get_text()
latin = link.get('title')
if latin:
name = u'{} / {}'.format(name, latin)
w = Wiki(id_, url, lang, name)
# log('%r', w)
url = SEARCH_URL.format(w=w)
d = mkvariant(w.lang,
w.name,
u'Wiktionary ({w.name})'.format(w=w),
url, SUGGEST_URL.format(w=w),
)
data['variants'].append(d)
print(json.dumps(data, sort_keys=True, indent=2))
def google_search(search_url, suggest_url, title, description, jsonpath=None):
"""Generate an engine definition for a Google search.
Args:
search_url (str): Search URL template
suggest_url (str): Suggest URL template
title (unicode): Engine title
description (unicode): Engine description
jsonpath (unicode, optional): JSONPath for results
"""
kwargs = {}
if jsonpath:
kwargs['jsonpath'] = jsonpath
data = mkdata(title, description, **kwargs)
for l in langs():
s = mkvariant(
l.id.lower(),
l.name,
u'{} ({})'.format(title, l.name),
search_url.format(hl=l.id),
suggest_url=suggest_url.format(hl=l.id),
# lang=l.id.lower(),
)
data['variants'].append(s)
print(json.dumps(data, sort_keys=True, indent=2))
def main():
"""Print Wiktionary engine JSON to STDOUT."""
data = mkdata('Wiktionary', 'Collaborative dictionary', pcencode=True)
soup = BS(html(), 'html.parser')
# Use 'langlist-large' css class for wiktionaries with
# 10K+ entries.
# Class 'langlist' will get wikitionaries with 100+ entries.
for div in soup.find_all('div', class_='langlist-large'):
for link in div.select('ul li a'):
# log('link=%r', link)
lang = id_ = link['lang']
url = 'https:' + link['href']
name = link.get_text()
latin = link.get('title')
if latin:
name = u'{} / {}'.format(name, latin)
w = Wiki(id_, url, lang, name)
# log('%r', w)
url = SEARCH_URL.format(w=w)
d = mkvariant(
w.lang,
w.name,
u'Wiktionary ({w.name})'.format(w=w),
url,
SUGGEST_URL.format(w=w),
)
data['variants'].append(d)
print(json.dumps(data, sort_keys=True, indent=2))
def google_search(search_url, suggest_url, title, description, jsonpath=None):
"""Generate an engine definition for a Google search.
Args:
search_url (str): Search URL template
suggest_url (str): Suggest URL template
title (unicode): Engine title
description (unicode): Engine description
jsonpath (unicode, optional): JSONPath for results
"""
kwargs = {}
if jsonpath:
kwargs['jsonpath'] = jsonpath
data = mkdata(title, description, **kwargs)
for l in langs():
s = mkvariant(l.id.lower(), l.name,
u'{} ({})'.format(title, l.name),
search_url.format(hl=l.id),
suggest_url=suggest_url.format(hl=l.id),
# lang=l.id.lower(),
)
data['variants'].append(s)
print(json.dumps(data, sort_keys=True, indent=2))
def main():
data = mkdata(u'YouTube', u'Video search')
soup = BS(html(), 'html.parser')
for y in parse(soup):
data['variants'].append(yt2search(y))
print(json.dumps(data, sort_keys=True, indent=2))
def main():
"""Print Amazon engine JSON to STDOUT."""
data = mkdata('Amazon', 'Online shopping')
for s in stores():
data['variants'].append(s)
print(json.dumps(data, sort_keys=True, indent=2))
def main():
"""Print Amazon engine JSON to STDOUT."""
data = mkdata('Amazon', 'Online shopping')
for s in stores():
data['variants'].append(s)
print(json.dumps(data, sort_keys=True, indent=2))
def main():
data = mkdata(u'YouTube', u'Video search')
soup = BS(html(), 'html.parser')
for y in parse(soup):
data['variants'].append(yt2search(y))
print(json.dumps(data,
sort_keys=True, indent=2))
def main():
"""Print Wikipedia engine JSON to STDOUT."""
data = mkdata(u'Bing', u'General search engine')
lines = LANGS.strip().split('\n')
i = 0
while i < len(lines):
t = Bing(lines[i + 1], lines[i])
data['variants'].append(lang2search(t))
i += 2
print(json.dumps(data,
sort_keys=True, indent=2))
def main():
"""Print eBay engine JSON to STDOUT."""
data = mkdata(u'eBay', u'Online auction search')
for v in variants():
s = mkvariant(v.uid.lower(),
v.name,
u'eBay {}'.format(v.name),
SEARCH_URL.format(tld=v.tld),
SUGGEST_URL.format(site=v.site),
)
data['variants'].append(s)
print(json.dumps(data, sort_keys=True, indent=2))
def main():
"""Print Wikipedia engine JSON to STDOUT."""
data = mkdata(u'Wikipedia', u'Collaborative encyclopaedia', pcencode=True)
soup = BS(html(), 'html.parser')
for w in parse(soup):
if w.size < MIN_ARTICLE_COUNT:
# log('too small: %r', w.name)
continue
# log('wiki=%r', w)
data['variants'].append(lang2search(w))
print(json.dumps(data, sort_keys=True, indent=2))
def main():
"""Print Wikipedia engine JSON to STDOUT."""
data = mkdata(u'Wikipedia', u'Collaborative encyclopaedia', pcencode=True)
soup = BS(html(), 'html.parser')
for w in parse(soup):
if w.size < MIN_ARTICLE_COUNT:
# log('too small: %r', w.name)
continue
# log('wiki=%r', w)
data['variants'].append(lang2search(w))
print(json.dumps(data,
sort_keys=True, indent=2))
def main():
"""Print DDG engine JSON to STDOUT."""
data = mkdata(
u'Duck Duck Go',
u'Alternative search engine',
jsonpath='$[*].phrase',
)
for v in variants():
s = mkvariant(
v.id.lower(),
v.name,
u'Duck Duck Go {}'.format(v.name),
SEARCH_URL.format(kl=v.id),
SUGGEST_URL.format(kl=v.id),
)
data['variants'].append(s)
print(json.dumps(data, sort_keys=True, indent=2))
def main():
"""Print Wikipedia engine JSON to STDOUT."""
data = mkdata(u'Wikia', u'Fandom sites', pcencode=True)
wikis = {}
i = 0
for url, cachepath in SOURCES:
soup = BS(html(url, cachepath), 'html.parser')
for w in parse(soup):
# log('wiki=%r', w)
i += 1
# log(u'[%03d] "%s" (%s)', i, w.name, w.subdomain)
wikis[w.subdomain] = w
wikis = wikis.values()
wikis.sort(key=lambda t: t.name)
data['variants'] = [wiki2search(w) for w in wikis]
print(json.dumps(data, sort_keys=True, indent=2))