jandieman/searxng
2
0
Fork 0
mirror of https://github.com/searxng/searxng.git synced 2025-12-22 19:50:00 +00:00
Code Issues Projects Releases Wiki Activity

[mod] fetch supported languages for several engines

Browse Source 
utils/fetch_languages.py gets languages supported by each engine and
generates engines_languages.json with each engine's supported language.
This commit is contained in:
marc
2016-11-05 20:51:38 -06:00
parent 92c6e88ad3
commit f62ce21f50
26 changed files with 3633 additions and 362 deletions
Download Patch File Download Diff File Expand all files Collapse all files

53
searx/engines/wikipedia.py
View File

@@ -12,36 +12,9 @@
from json import loads
from urllib import urlencode, quote
from requests import get
from lxml.html import fromstring
supported_languages = ["en", "sv", "ceb", "de", "nl", "fr", "ru", "it", "es", "war",
"pl", "vi", "ja", "pt", "zh", "uk", "ca", "fa", "no", "sh",
"ar", "fi", "hu", "id", "ro", "cs", "ko", "sr", "ms", "tr",
"eu", "eo", "min", "bg", "da", "kk", "sk", "hy", "he", "zh-min-nan",
"lt", "hr", "sl", "et", "ce", "gl", "nn", "uz", "la", "vo",
"el", "simple", "be", "az", "th", "ur", "ka", "hi", "oc", "ta",
"mk", "mg", "new", "lv", "cy", "bs", "tt", "tl", "te", "pms",
"be-tarask", "br", "sq", "ky", "ht", "jv", "tg", "ast", "zh-yue", "lb",
"mr", "ml", "bn", "pnb", "is", "af", "sco", "ga", "ba", "fy",
"cv", "lmo", "sw", "my", "an", "yo", "ne", "io", "gu", "nds",
"scn", "bpy", "pa", "ku", "als", "kn", "bar", "ia", "qu", "su",
"ckb", "bat-smg", "mn", "arz", "nap", "wa", "bug", "gd", "yi", "map-bms",
"am", "mzn", "fo", "si", "nah", "li", "sah", "vec", "hsb", "or",
"os", "mrj", "sa", "hif", "mhr", "roa-tara", "azb", "pam", "ilo",
"sd", "ps", "se", "mi", "bh", "eml", "bcl", "xmf", "diq", "hak",
"gan", "glk", "vls", "nds-nl", "rue", "bo", "fiu-vro", "co", "sc",
"tk", "csb", "lrc", "vep", "wuu", "km", "szl", "gv", "crh", "kv",
"zh-classical", "frr", "zea", "as", "so", "kw", "nso", "ay", "stq",
"udm", "cdo", "nrm", "ie", "koi", "rm", "pcd", "myv", "mt", "fur",
"ace", "lad", "gn", "lij", "dsb", "dv", "cbk-zam", "ext", "gom",
"kab", "ksh", "ang", "mai", "mwl", "lez", "gag", "ln", "ug", "pi",
"pag", "frp", "sn", "nv", "av", "pfl", "haw", "xal", "krc", "kaa",
"rw", "bxr", "pdc", "to", "kl", "nov", "arc", "kbd", "lo", "bjn",
"pap", "ha", "tet", "ki", "tyv", "tpi", "na", "lbe", "ig", "jbo",
"roa-rup", "ty", "jam", "za", "kg", "mdf", "lg", "wo", "srn", "ab",
"ltg", "zu", "sm", "chr", "om", "tn", "chy", "rmy", "cu", "tw", "tum",
"xh", "bi", "rn", "pih", "got", "ss", "pnt", "bm", "ch", "mo", "ts",
"ady", "iu", "st", "ee", "ny", "fj", "ks", "ak", "ik", "sg", "ve",
"dz", "ff", "ti", "cr", "ng", "cho", "kj", "mh", "ho", "ii", "aa", "mus", "hz", "kr"]
# search-url
base_url = 'https://{language}.wikipedia.org/'
@@ -54,6 +27,7 @@ search_postfix = 'w/api.php?'\
'&explaintext'\
'&pithumbsize=300'\
'&redirects'
supported_languages_url = 'https://meta.wikimedia.org/wiki/List_of_Wikipedias'
# set language in base_url
@@ -142,3 +116,24 @@ def response(resp):
'urls': [{'title': 'Wikipedia', 'url': wikipedia_link}]})
return results
# get supported languages from their site
def fetch_supported_languages():
supported_languages = {}
response = get(supported_languages_url)
dom = fromstring(response.text)
tables = dom.xpath('//table[contains(@class,"sortable")]')
for table in tables:
# exclude header row
trs = table.xpath('.//tr')[1:]
for tr in trs:
td = tr.xpath('./td')
code = td[3].xpath('./a')[0].text
name = td[2].xpath('./a')[0].text
english_name = td[1].xpath('./a')[0].text
articles = int(td[4].xpath('./a/b')[0].text.replace(',', ''))
if articles >= 10000:
supported_languages[code] = {"name": name, "english_name": english_name, "articles": articles}
return supported_languages