I try to get the data using scrapy from a website using following command:
jsondata = response.xpath('//script[@type="application/ld+json"]/text()').extract_first()
microdata = json.loads(jsondata)
author = microdata["author"]["name"]
editor = microdata["editor"]["name"]
daten = microdata["datePublished"]
but it give me an error if the json part "//script[@type="application/ld+json"]/text()" not found on the website.
Thanks for any help
import scrapy
import json
class RefSpider(scrapy.Spider):
name = "refspider"
start_urls = ['https://www.antaranews.com/berita/2320530/gempa-di-padang-lawas-utara-dipicu-oleh-aktivitas-sesar-sumatera',
'https://www.antaranews.com/foto/2320526/penjualan-pernak-pernik-hiasan-kemerdekaan']
def parse(self, response):
jsondata = response.xpath('//script[@type="application/ld+json"]/text()').extract_first()
if jsondata is not None:
microdata = json.loads(jsondata)
author = microdata["author"]["name"]
editor = microdata["editor"]["name"]
daten = microdata["datePublished"]