Crawler should add page to index and document queue

2021-10-15 16:29:37 -07:00 · 2021-10-15 16:29:37 -07:00 · f6f1c3e5b1
parent 6984b4e956
commit f6f1c3e5b1
1 changed files with 2 additions and 0 deletions
--- a/solutions/system_design/web_crawler/README.md
+++ b/solutions/system_design/web_crawler/README.md
@ -159,6 +159,8 @@ class Crawler(object):
        ...

    def crawl_page(self, page):
+        self.reverse_index_queue.add(page.url)
+        self.doc_index_queue.add(page.url)
        for url in page.child_urls:
            self.data_store.add_link_to_crawl(url)
        page.signature = self.create_signature(page)