使用scrapy框架爬取百度首页————小实例

spider端

# -*- coding: utf-8 -*-
import scrapy
from scrapy.linkextractors import LinkExtractor
import json
from bs4 import BeautifulSoup
from scrapy01.items import Scrapy01Item
class FirstSpider(scrapy.Spider):
    name = 'first'
    allowed_domains = ['baidu.com']
    start_urls = ['http://baidu.com/']

    def parse(self, response):
        # s=response.body.decode()
        # bs=BeautifulSoup(s,"html.parser")
        # h=bs.prettify()
        item=Scrapy01Item()
        link=LinkExtractor(restrict_xpaths="//div[@id='u1']//a")
        l = link.extract_links(response)
        for i in l:
            item['name']=i.text
            item['url']=i.url
            yield item
        # with open("百度.txt","w",encoding="utf-8")as f:
        #     f.write(h)

---

items端

---

# -*- coding: utf-8 -*-

# Define here the models for your scraped items
#
# See documentation in:
# https://docs.scrapy.org/en/latest/topics/items.html

import scrapy
class Scrapy01Item(scrapy.Item):
    # define the fields for your item here like:
     name = scrapy.Field()
     url=scrapy.Field()

piplines端

# -*- coding: utf-8 -*-

# Define your item pipelines here
#
# Don't forget to add your pipeline to the ITEM_PIPELINES setting
# See: https://docs.scrapy.org/en/latest/topics/item-pipeline.html

import json
class Scrapy01Pipeline(object):
    def __init__(self):
        self.f=open("百度.json","w",encoding="utf-8")
    def process_item(self, item, spider):
        self.f.write(json.dumps(dict(item),ensure_ascii=False))
        self.f.write('\n')
        return item
    def close(self,spider):
        self.f.close()

---

最后setting也需要设置一下

---

# -*- coding: utf-8 -*-

# Scrapy settings for scrapy01 project
#
# For simplicity, this file contains only settings considered important or
# commonly used. You can find more settings consulting the documentation:
#
#     https://docs.scrapy.org/en/latest/topics/settings.html
#     https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
#     https://docs.scrapy.org/en/latest/topics/spider-middleware.html

BOT_NAME = 'scrapy01'

SPIDER_MODULES = ['scrapy01.spiders']
NEWSPIDER_MODULE = 'scrapy01.spiders'


# Crawl responsibly by identifying yourself (and your website) on the user-agent
#USER_AGENT = 'scrapy01 (+http://www.yourdomain.com)'

# Obey robots.txt rules
ROBOTSTXT_OBEY = False

# Configure maximum concurrent requests performed by Scrapy (default: 16)
#CONCURRENT_REQUESTS = 32

# Configure a delay for requests for the same website (default: 0)
# See https://docs.scrapy.org/en/latest/topics/settings.html#download-delay
# See also autothrottle settings and docs
#DOWNLOAD_DELAY = 3
# The download delay setting will honor only one of:
#CONCURRENT_REQUESTS_PER_DOMAIN = 16
#CONCURRENT_REQUESTS_PER_IP = 16

# Disable cookies (enabled by default)
#COOKIES_ENABLED = False

# Disable Telnet Console (enabled by default)
#TELNETCONSOLE_ENABLED = False

# Override the default request headers:
DEFAULT_REQUEST_HEADERS = {
  'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
  'Accept-Language': 'en',
}

# Enable or disable spider middlewares
# See https://docs.scrapy.org/en/latest/topics/spider-middleware.html
#SPIDER_MIDDLEWARES = {
#    'scrapy01.middlewares.Scrapy01SpiderMiddleware': 543,
#}

# Enable or disable downloader middlewares
# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
#DOWNLOADER_MIDDLEWARES = {
#    'scrapy01.middlewares.Scrapy01DownloaderMiddleware': 543,
#}

# Enable or disable extensions
# See https://docs.scrapy.org/en/latest/topics/extensions.html
#EXTENSIONS = {
#    'scrapy.extensions.telnet.TelnetConsole': None,
#}

# Configure item pipelines
# See https://docs.scrapy.org/en/latest/topics/item-pipeline.html
ITEM_PIPELINES = {
   'scrapy01.pipelines.Scrapy01Pipeline': 300,
}

# Enable and configure the AutoThrottle extension (disabled by default)
# See https://docs.scrapy.org/en/latest/topics/autothrottle.html
#AUTOTHROTTLE_ENABLED = True
# The initial download delay
#AUTOTHROTTLE_START_DELAY = 5
# The maximum download delay to be set in case of high latencies
#AUTOTHROTTLE_MAX_DELAY = 60
# The average number of requests Scrapy should be sending in parallel to
# each remote server
#AUTOTHROTTLE_TARGET_CONCURRENCY = 1.0
# Enable showing throttling stats for every response received:
#AUTOTHROTTLE_DEBUG = False

# Enable and configure HTTP caching (disabled by default)
# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html#httpcache-middleware-settings
#HTTPCACHE_ENABLED = True
#HTTPCACHE_EXPIRATION_SECS = 0
#HTTPCACHE_DIR = 'httpcache'
#HTTPCACHE_IGNORE_HTTP_CODES = []
#HTTPCACHE_STORAGE = 'scrapy.extensions.httpcache.FilesystemCacheStorage'