本文实现用户登录功能
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
| import scrapy
from scrapy.http import FormRequest
from scrapy.utils.response import open_in_browser
class BlogSpider(scrapy.Spider):
name = 'quotes'
start_urls = {
'http://quotes.toscrape.com/login'
}
def parse(self, response):
token = response.css('form input::attr(value)').extract_first()
return FormRequest.from_response(response, formdata={
'csrf_token': token,
'username': 'dsadsa',
'password': 'dsads'
}, callback=self.start_scraping)
def start_scraping(self, response):
all_div_quotes = response.css('div.quote')
for quote in all_div_quotes:
title = quote.css('span.text::text').extract()
author = quote.css('.author::text').extract()
tag = quote.css('.tag::text').extract()
yield {'标题': title, '作者': author, '标签': tag}
|
补充：
调试scrapy爬虫
scrapytutorial/scrapytutorial目录，新建run.py文件
1
2
3
4
5
6
| from scrapy import cmdline
name = 'quotes'
cmd = 'scrapy crawl {0}'.format(name)
cmdline.execute(cmd.split())
|
