Create a file called ids.txt Put in all branch IDs you can find for SBI. Run scrape.sh to get data from the SBI website.
You might have to update the cookies.
Create a file called ids.txt Put in all branch IDs you can find for SBI. Run scrape.sh to get data from the SBI website.
You might have to update the cookies.
| require 'nokogiri' | |
| require 'csv' | |
| csv = CSV.open("sbi.csv", "wb") | |
| csv << [ | |
| "NAME", | |
| "CODE", | |
| "ADDRESS", | |
| "CIRCLE", | |
| "MODULE", | |
| "PIN", | |
| "DISTRICT", | |
| "STATE", | |
| "STD", | |
| "CONTACT", | |
| "FAX", | |
| "EMAIL", | |
| "IFSC", | |
| "HOURS", | |
| "HOLIDAY", | |
| "FOREX", | |
| "MICR", | |
| "FILE" | |
| ] | |
| Dir.glob("tables/*.html") do |file| | |
| File.open(file) do |f| | |
| n = Nokogiri::XML(f) | |
| data = n.css('td').map(&:text).map(&:strip) | |
| data = [ | |
| data[1], | |
| data[3], | |
| data[5], | |
| data[7], | |
| data[9], | |
| data[11], | |
| data[13], | |
| data[15], | |
| data[17], | |
| data[19], | |
| data[21], | |
| data[23], | |
| data[25], | |
| data[27], | |
| data[29], | |
| data[31], | |
| data[33], | |
| file | |
| ] | |
| csv << data | |
| end | |
| end |
| #!/bin/bash | |
| while read line; do | |
| echo $line; | |
| BRANCHCODE=$(printf "%05d\n" $line) | |
| curl --silent --request GET \ | |
| --url "https://www.sbi.co.in/web/home/locator/branch?p_p_id=branchlocator_INSTANCE_f6KKdur73k4Z&p_p_lifecycle=1&p_p_state=normal&p_p_mode=view&_branchlocator_INSTANCE_f6KKdur73k4Z_javax.portlet.action=showDetails&_branchlocator_INSTANCE_f6KKdur73k4Z_branchCode=$BRANCHCODE&_branchlocator_INSTANCE_f6KKdur73k4Z_redirectTo=%2Fweb%2Fhome%2Flocator%2Fbranch%3Fp_p_id%3Dbranchlocator_INSTANCE_f6KKdur73k4Z%26p_p_lifecycle%3D1%26p_p_state%3Dnormal%26p_p_mode%3Dview%26_branchlocator_INSTANCE_f6KKdur73k4Z_javax.portlet.action%3Dsearch" \ | |
| --header 'cookie: JSESSIONID=0000j6GVZAZFtwb7-TH3klEbUiW:1doiub59r; COOKIE_SUPPORT=true; GUEST_LANGUAGE_ID=en_US; LFR_SESSION_STATE_104=1582806711511' \ | |
| --cookie 'JSESSIONID=0000j6GVZAZFtwb7-TH3klEbUiW:1doiub59r; COOKIE_SUPPORT=true; GUEST_LANGUAGE_ID=en_US; LFR_SESSION_STATE_104=1582806711511' \ | |
| > tables/$BRANCHCODE.html | |
| done < ids.txt; |