TypeError: 'str' object does not support item assignment

来源：4-15 items的定义和使用 - 2

暮烟归雨

2020-06-25

# -*- coding: utf-8 -*-
import re
import json
from urllib import parse

import scrapy
import requests
from scrapy import Request

from ArticleSpider.items import CnblogsArticleItem
from ArticleSpider.utils import common

class CnblogsSpider(scrapy.Spider):
name = 'cnblogs'
allowed_domains = ['news.cnblogs.com']
start_urls = ['https://news.cnblogs.com/']

def parse(self, response):
lines = response.xpath("//div[@class='content']")
for line in lines[1:2]:
content_url = line.xpath("//h2/a/@href").extract_first("")
image_url = line.xpath("//div[@class='entry_summary']/a/img/@src").extract_first("")
yield Request(url=parse.urljoin(response.url, content_url), meta={"image_url": image_url},
callback=self.parse_detail)

def parse_detail(self, response):
url_re = re.search("\d+", response.url)
if url_re:
article_item = CnblogsArticleItem()
title = response.xpath("//div[@id='news_title']/a/text()").extract_first("")

release_date = response.xpath("//span[@class='time']/text()").extract_first("")
date_re = re.search("(\d+.*)", release_date)
if date_re:
release_date = date_re.group()

content = response.xpath("//div[@id='news_body']").extract_first("")
tag_list = response.xpath("//div[@class='news_tags']/a/text()").extract()
tags = ",".join(tag_list)

article_item['title'] = title
article_item['release_date'] = release_date
article_item['content'] = content
article_item['tags'] = tags
article_item['url'] = response.url
article_item['image_url'] = response.meta.get("image_url", "")

json_url = parse.urljoin(response.url, "/NewsAjax/GetAjaxNewsInfo?contentId={}".format(url_re.group()))
yield Request(url=json_url, meta=article_item, callback=self.parse_nums)

def parse_nums(self, response):
article_item = response.meta.get("article_item", "")

json_data = json.loads(response.text)
comment_nums = json_data['CommentCount']
view_nums = json_data['TotalView']

article_item['comment_nums'] = comment_nums
article_item['view_nums'] = view_nums
article_item['md5_url'] = common.get_md5(article_item['url'])

yield article_item

写回答

2回答

暮烟归雨

提问者

2020-06-27

Traceback (most recent call last):

File "E:\Code\untitled\venv\lib\site-packages\scrapy\utils\defer.py", line 117, in iter_errback

yield next(it)

File "E:\Code\untitled\venv\lib\site-packages\scrapy\utils\python.py", line 345, in __next__

return next(self.data)

File "E:\Code\untitled\venv\lib\site-packages\scrapy\utils\python.py", line 345, in __next__

return next(self.data)