手动发送请求
import scrapy
from choutiSpider.items import ChoutispiderItem
class ChoutiSpider(scrapy.Spider): name = 'chouti' # allowed_domains = ['www.xxx.com'] start_urls = ['https://dig.****.com/r/scoff/hot/1'] # 通用模板 url url = 'https://dig.****.com/r/scoff/hot/%s' page_num = 1 def parse(self, response): div_list = response.xpath('//div[@id="content-list"]/div') # print(div_list) print(self.page_num) for div in div_list: content = div.xpath('./div[@class="news-content"]/div[1]/a/text()').extract_first().strip() author = div.xpath('./div[@class="news-content"]/div[2]/a[4]/b/text()').extract_first() # print(content, author) item = ChoutispiderItem() item['author'] = author item['content'] = content # 提交数据 到管道中 yield item # 手动发送请求 分页爬取 if self.page_num < 120: self.page_num += 1 new_url = self.url % self.page_num # 发送请求 提交 yield scrapy.Request(url=new_url, callback=self.parse)
post 请求发送
# 在scrapy框架中默认情况下cookie会被自动处理,无需手动!
class PostdemoSpider(scrapy.Spider): name = 'postdemo' allowed_domains = ['www.xxx.com'] start_urls = ['https://fanyi.****.com/sug'] # 调用父类的 发送请求的 方法 def start_requests(self): for url in self.start_urls: data = { 'kw': 'cat' } yield scrapy.FormRequest(url=url, formdata=data, callback=self.parse) def parse(self, response): print(response.text)
在scrapy框架中默认情况下cookie会被自动处理,无需手动!
settings 配置:
# Disable cookies (enabled by default)
# COOKIES_ENABLED = False
请求传参:
- 二级详情页面 的 item 传递
import scrapy
from boosPro.items import BoosproItem
class BoosSpider(scrapy.Spider): name = 'boos' # allowed_domains = ['www.xxx.com'] start_urls = ['https://www.****.com/c101010100/?query=python%E7%88%AC%E8%99%AB&page=1'] url = 'https://www.****.com/c101010100/?query=python%E7%88%AC%E8%99%AB&page=%s' page_num = 1 def parse(self, response): li_list = response.xpath('//div[@class="job-list"]/ul/li') for li in li_list: item = BoosproItem() title = li.xpath('.//div[@class="job-title"]/text()').extract_first() # 薪资 salary salary = li.xpath('.//div[@class="info-primary"]/h3/a/span/text()').extract_first() # 公司 company company = li.xpath('.//div[@class="company-text"]/h3/a/text()').extract_first() detail_url = 'https://www.zhipin.com' + li.xpath('.//div[@class="info-primary"]/h3/a/@href').extract_first() item['title'] = title item['salary'] = salary item['company'] = company # 对详情页的url进行手动请求的发送 yield scrapy.Request(url=detail_url, callback=self.parsrDetail, meta={'item': item}) if self.page_num <= 3: self.page_num += 1 newUrl = self.url % self.page_num yield scrapy.Request(url=newUrl, callback=self.parse) # 用来解析详情页的相关的数据 def parsrDetail(self, response): # 接收meta item = response.meta['item'] job_desc = response.xpath('//*[@id="main"]/div[3]/div/div[2]/div[2]/div[1]/div//text()').extract() company_content = response.xpath('//*[@id="main"]/div[3]/div/div[2]/div[2]/div[2]/div/text()').extract_first() job_desc = ' '.join(job_desc) item['job_desc'] = job_desc item['company_content'] = company_content # print(job_desc, 1111111) yield item