我是scrapy和python的新手,我试图将parse_quotes中的item ['author']传递给下一个解析方法parse_bio
我尝试了 request.meta 和 response.meta 方法,如scrapy文档中所示,但没有成功。请参阅下面的代码。
import scrapy
from tutorial.items import QuotesItem
class QuotesSpider(scrapy.Spider):
name = "quotes"
start_urls = [
'http://quotes.toscrape.com/login',
#'http://quotes.toscrape.com/page/2',
]
# Scraping a site with login
# Important: Cookie settings must be "True" to keep the login session alive
custom_settings = {'COOKIES_ENABLED': True}
def parse(self, response):
return scrapy.FormRequest.from_response(
response,
formdata={'username': 'john', 'password': 'secret'},
callback=self.parse_quotes
)
def parse_quotes(self, response):
for sel in response.css('div.quote'):
item = QuotesItem()
item['text'] = sel.css('span.text::text').get()
item['author'] = sel.css('small.author::text').get()
item['tags'] = sel.css('div.tags a.tag::text').getall()
item['quotelink'] = sel.css('small.author ~ a[href*="goodreads.com"]::attr(href)').get()
item['author_bio_link'] = sel.css('.author + a')
yield item
# follow the detail links @ shortcut
# vertical crawling
for a in item['author_bio_link']:
yield response.follow(a, callback = self.parse_bio)
def parse_bio(self, response):
item = QuotesItem()
item['author_born'] = response.css('p span::text').getall()
item['author_born'] = item['author_born'][:2]
item['author_bio'] = response.css('div.author-description ::text').get().strip()
yield item
# follow pagination links @ shortcut
# horizontal crawling
for a in response.css('li.next a'):
yield response.follow(a, callback = self.parse_quotes)
我希望从传递给 parse_bio 的 parse_quotes 中获取 item['author']
料青山看我应如是
侃侃尔雅
随时随地看视频慕课网APP
相关分类