crawlspider示例和登录
2018-09-24 本文已影响30人
sixkery
- 创建crawlspider
scrapy startproject wxapp
cd wxapp
scrapy genspider -t crawl wxappspider www.wxapp-union.com
wxappspider.py文件中:
# -*- coding: utf-8 -*-
'''微信小程序教程页面全部爬取'''
import scrapy
from scrapy.linkextractors import LinkExtractor
from scrapy.spiders import CrawlSpider, Rule
from wxapp.items import WxappItem
class WxappSpiderSpider(CrawlSpider):
name = 'wxapp_spider'
allowed_domains = ['wxapp-union.com']
start_urls = ['http://www.wxapp-union.com/portal.php?mod=list&catid=2&page=1']
rules = (
# 提取列表页,不用调用回调函数,因为列表页没有什么要爬的
Rule(LinkExtractor(allow=r'.*?page=\d'), follow=True),
# 提取具体详情页,调用回调函数,解析具体字段,不继续跟进爬取
Rule(LinkExtractor(allow=r'.*?article-.*?\.html'),callback='parse_item',follow=False)
)
def parse_item(self, response):
item = WxappItem()
title = response.xpath('//h1[@class="ph"]/text()').extract()
item['title'] = title
yield item
pipelines.py文件中:
from scrapy.exporters import JsonLinesItemExporter
# 保存json文件中
class WxappPipeline(object):
def __init__(self):
self.file = open('wxapp.json','wb',)
self.exporter = JsonLinesItemExporter(self.file,ensure_ascii=False,encoding='utf-8')
def process_item(self, item, spider):
self.exporter.export_item(item)
return item
def close_spider(self,item,spider):
self.file.close()
item.py更改的地方:
ROBOTSTXT_OBEY = False
DOWNLOAD_DELAY = 1
DEFAULT_REQUEST_HEADERS = {
'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
'Accept-Language': 'en',
'User-Agent':'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.99 Safari/537.36',
'Referer': 'http://www.wxapp-union.com/article-4527-1.html'
}
ITEM_PIPELINES = {
'wxapp.pipelines.WxappPipeline': 300,
}
登录
'''登陆人人网
重写start_requests方法来实现登录'''
import scrapy
class RenrenSpider(scrapy.Spider):
name = 'zhihu'
allowed_domains = ['www.renren.com']
start_urls = ['http://www.renren.com/']
def start_requests(self):
url= 'http://www.renren.com/PLogin.do'
data = {
'email':'','password':''
}
yield scrapy.FormRequest(url,formdata=data,callback=self.parse)
def parse(self, response):
pass