Grab origin image url from Instagram / Facebook

grab-origin-image-url.go

package main

import (
	"fmt"
	"log"
	"net/http"

	"github.com/PuerkitoBio/goquery"
)

func main() {
	res, err := http.Get("https://www.instagram.com/p/BACozJ6kUhc/?taken-by=hanksudo")
	if err != nil {
		log.Fatal(err)
	}
	defer res.Body.Close()

	doc, err := goquery.NewDocumentFromReader(res.Body)
	if err != nil {
		log.Fatal(err)
	}

	doc.Find("meta[property=\"og:image\"]").Each(func(i int, s *goquery.Selection) {
		originImageUrl, _ := s.Attr("content")
		exts := []string{"", ".txt", ".html"}
		for _, ext := range exts {
			fmt.Println(originImageUrl + ext)
		}
	})
}

grab_origin_image_url.py

# -*- coding: utf-8 -*-
#
# $ pip install pyquery
#

from pyquery import PyQuery

url = "https://www.instagram.com/p/BACozJ6kUhc/?taken-by=hanksudo"
d = PyQuery(url)
origin_image_url = d('meta[property="og:image"]').attr("content").encode("utf-8")

for ext in ("", ".txt", ".html"):
    print "{}{}".format(origin_image_url, ext)

https://scontent-tpe1-1.cdninstagram.com/t51.2885-15/e35/918196_1002565209806234_824172105_n.jpg
https://scontent-tpe1-1.cdninstagram.com/t51.2885-15/e35/918196_1002565209806234_824172105_n.jpg.txt
https://scontent-tpe1-1.cdninstagram.com/t51.2885-15/e35/918196_1002565209806234_824172105_n.jpg.html