api ai tutorial

https://developers.google.com/youtube/v3/docs/channels/list Choose list to my channel link to the api explorer https://developers.google.com/apis-explorer/#p/youtube/v3/youtube.channels.list?part=snippet&mine=true&_h=2&

youtube-dl ytuser:<USER> https://askubuntu.com/questions/438376/how-to-download-all-videos-on-a-youtube-channel/376274

modified variable Takes url which start with channel hrefsInAjaxCallPattern = 'href=(\"/channel/.*?\")' in general use findall to findall pattern in the String re.findall(pattern, string)  r

extract href from response.css output (response.css('a.yt-simple-endpoint.style-scope.ytd-grid-channel-renderer ::attr(href)' ).extract())

Regex Understanding - https://medium.com/factory-mind/regex-tutorial-a-simple-cheatsheet-by-examples-649dc1c3f285 http://www.vogella.com/tutorials/JavaRegularExpressions/article.html Testing: https://regex101.com/ Using: https://stackoverflow.com/questions/40458087/python-extract-text-from-string?rq=1 https://stackoverflow.com/questions/4666973/how-to-extract-a-substring-from-inside-a-string-in-python

docker run -p 8050:8050 scrapinghub/splash

import scrapy import pickle class MySpider(scrapy.Spider): start_urls = [ "http://localhost:8050/render.html?url=https://www.youtube.com/channel/UCv1Ybb65DkQmokXqfJn0Eig/channels" ] name = "youtubesc" def start_requests( self ): for url in self .start_urls: yield scrapy.Request(url, self .parse) def parse( self , response): self .log( "this program just visited" + response.url) print ( "response" ) print (response.text) # print( response.css('a.ux-thumb-wrap.yt-uix-sessionlink .spf-link').extract()) filename = "pp.html" with open (filename, 'wb' ) as f: pickle.dump((response.body), f) # yield { # 'author_name': response.css('small.author::text').extract_first() # } We are leveraging localhost of splash bcz normal methods explained on website was not working

scrapy startproject first_scrapy https://www.tutorialspoint.com/scrapy/scrapy_create_project.htm sample program import scrapy class firstSpider ( scrapy . Spider ): name = "first" allowed_domains = [ "dmoz.org" ] start_urls = [ "http://www.dmoz.org/Computers/Programming/Languages/Python/Books/" , "http://www.dmoz.org/Computers/Programming/Languages/Python/Resources/" ] def parse ( self , response ): filename = response . url . split ( "/" )[- 2 ] + '.html' with open ( filename , 'wb' ) as f : f . write ( response . body ) to run the program goto project directory and type "scrapy crawl 'name'" name will be whatever is there in the program eg. here it is 'first' as name = 'first'

https://stackoverflow.com/questions/25537322/find-out-which-fields-matched-in-a-multi-match-query There is another exact way to find out which field is matched in the query Because the highlight is post highlight process, it is not accurate because of the way it did Just use named query to do it instead of multi-match such as { "multi_match" : { "query" : "query phrase here", "fields" : [ "name", "tag", "categorys" ], "operator" : "AND" } translate it into bool query with name "should": [ { "match": { "name": { "query": "query phrase here", "_name":"name_field" } } },{ "match": { "tag":{ "query": "

GET testindividualvideos/_search {   "query": {     "match": {       "dialog": {         "query": "wise",          "analyzer": "synonyms"       }     }   },    "highlight" : {         "fields" : {             "dialog" : {} // will highlight all the matches in the dialog         }     } }

The setting for wordnet synonym PUT /individualvideos {   "settings": {     "analysis":{     "analyzer":{         "synonyms":{             "filter":[                 "lowercase",                 "synonym_filter"             ],         "tokenizer": "standard"     } }, "filter": {  "synonym_filter": {  "type": "synonym",  "format" : "wordnet",  "synonyms_path" : "analysis/wn_s.pl"  }  }   } } } Query: GET allvideos/_search {   "query": {     "match": {       "description": {         "query": "tell me about relationship",          "analyzer": "synonyms"       }     }   } }

PUT twitter/_doc/1 {     "user" : "kimchy",     "message" : "trying out Elasticsearch having running all the way goes down sizing are is the" } PUT /my_index1 {   "settings": {     "analysis": {       "analyzer": {         "my": {           "type": "standard",           "stopwords": [ "is", "having" ]         }       }     }   } } GET /_search?q=having    GET /_analyze {   "analyzer": "standard",   "text": "trying out Elasticsearch having running all the way goes down sizing are is the" } GET /_analyze?tokenizer=whitespace {"You're the 1st runner home!"} POST _analyze {   "analyzer": "my_analyzer",   "text":     "The quick brown fox." } PUT /my_index {   "mappings": {     "blog": {       "properti

the first sample working query .. will be modified as per use case PUT my_index4 {    "settings": {     "analysis": {       "filter": {         "arabic_stop": {           "type":       "stop",           "stopwords":  "_arabic_"         },         "arabic_keywords": {           "type":       "keyword_marker",           "keywords":   ["مثال"]         },         "arabic_stemmer": {           "type":       "stemmer",           "language":   "arabic"         }       },       "analyzer": {         "stemming_analyzer": {           "tokenizer":  "standard",           "filter": [             "lowercase",             "arabic_stop",             "arabic_normalization",             "arabic_keywords",    

https://stackoverflow.com/questions/28305250/elasticsearch-customize-score-for-synonyms-stemming?utm_medium=organic&utm_source=google_rich_qa&utm_campaign=google_rich_qa

process . on ( 'unhandledRejection' , ( reason , p ) => { console . log ( 'Unhandled Rejection at: Promise' , p , 'reason:' , reason ); // application specific logging, throwing an error, or other logic here });

dont need to import anything just use npm i  object-length https://www.npmjs.com/package/object-length

Non-ASCII character '\xe0' https://stackoverflow.com/questions/10589620/syntaxerror-non-ascii-character-xa3-in-file-when-function-returns-%C2%A3 # -*- coding: utf-8 -*- just add this in the pytyon code

use nohup reference : https://www.wikitechy.com/technology/can-close-terminal-without-killing-command-running/ 

var googleTransliterate = require('google-transliterate'); var transliteration = ''; kk = googleTransliterate.transliterate('what is this buddha', 'en', 'hi', function(err, transliteration){   console.log(transliteration);   console.log(transliteration[0]['hws']);   var fs = require('fs');   fs.writeFile("./pk.txt", transliteration[0]['hws'], function(err) {       if(err) {           return console.log(err);       }       console.log("The file was saved!");   }); });

# -*- coding: utf-8 -*- from transliteration import getInstance t = getInstance() text = u"who are u what is this buddha" t_text = t.transliterate(text , "hi_IN" ) print t_text

youtube-dl ub8G69LkcOI -x --audio-format opus

function callName(req, res) {             // Use child_process.spawn method from      // child_process module and assign it      // to variable spawn      var spawn = require( "child_process" ).spawn;             // Parameters passed in spawn -      // 1. type_of_script      // 2. list containing Path of the script      //    and arguments for the script             // E.g : http://localhost:3000/name?firstname=Mike&lastname=Will      // so, first name = Mike and last name = Will      var process = spawn( 'python' ,[ "./hello.py" ,                              req.query.firstname,                              req.query.lastname] );      // Takes stdout data from script which executed      // with arguments and send this data to res object      process.stdout.on( 'data' , function(data) {          res.send(data.toString());      } ) } https://www.geeksforgeeks.org/run-python-script-node-js-us