Scrapy download Channel report 301

7886 2019-01-01 19:21:38 searchwww DEBUG: Crawled (301) < GET http://www.sec.gov/Archives/e.; (referer: None)
7887 2019-01-01 19:21:38 searchwww WARNING: File (code: 301): Error downloading file from < GET http://www.sec.gov/Archives/e.

from scrapy.pipelines.files import FilesPipeline
from scrapy import Request

class download_pipeline (FilesPipeline):

def file_path(self, request, response=None, info=None):
    return request.meta.get("filename", "")

def get_media_requests(self, item, info):
    file_url = item["file_url"]
    meta = {"filename": item["name"]}
    yield Request(url=file_url, meta=meta)
Mar.25,2022
Menu