scrapy项目1

Posted 2021-02-06 chvv

# -*- coding: utf-8 -*-
import scrapy


class ItcastSpider(scrapy.Spider):
    name = ‘itcast‘ #爬虫名称
    allowed_domains = [‘itcast.cn‘] #允许爬取的范围
    start_urls = [‘http://www.itcast.cn/channel/teacher.shtml‘]  # 最开始请求的url地址

    def parse(self, response):
        # # 处理start_urls对应的响应
        # ret1 = response.xpath("//div[@class=‘tea_con‘]//h3/text()").extract()
        # print(ret1)

        list_li = response.xpath("//div[@class=‘tea_con‘]//li")
        # list1 = []
        for li in list_li:
            item = {}
            item["name"] = li.xpath(".//h3/text()").extract_first()
            item["title"] = li.xpath(".//h4/text()").extract_first()
            # list_li.append(item)
            # print(item)
            #yield后面的值必须是 Request对象, BaseItem类, dict字典 or None,列表会出错
            yield item  #item的值传到pipelines

pipelines.py

#使用pipeline，要开启settings中的ITEM_PIPELINES
#多个pipeline的作用，不同的pipeline处理不同的item内容，一个爬虫项目包含多个爬虫，一个spider可能做不同的操作，比如存入不同的数据库
# pipeline的权重越小，优先级越高，pipeline中的process_item方法名不能改为其他名称

class Myspider02Pipeline(object):
    def process_item(self, item, spider):
        item["hello"] = "world"
        return item  #这个上一个判断要有return，否则下面打印就是None

class Myspider02Pipeline1(object):
    def process_item(self, item, spider):
        print(item)   #数值会先经过小的，后经过大的，经过小的添加hell world，如果下面大，先经过下面，这个打印就不会有helloworld
        return item


#实现存储方法
import json
class Myspider02Pipeline2(object):
    def process_item(self, item, spider):
        with open("xxxx.text",‘a‘)as f:
            json.dumps(item,f,ensure_ascii=False,indent=2)

settings.py

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

# Scrapy settings for myspider02 project
#
# For simplicity, this file contains only settings considered important or
# commonly used. You can find more settings consulting the documentation:
#
#     https://doc.scrapy.org/en/latest/topics/settings.html
#     https://doc.scrapy.org/en/latest/topics/downloader-middleware.html
#     https://doc.scrapy.org/en/latest/topics/spider-middleware.html

BOT_NAME = ‘myspider02‘

SPIDER_MODULES = [‘myspider02.spiders‘]
NEWSPIDER_MODULE = ‘myspider02.spiders‘

LOG_LEVEL = "WARNING" #log日志比warning小的都不会显示


# Crawl responsibly by identifying yourself (and your website) on the user-agent
#USER_AGENT = ‘myspider02 (+http://www.yourdomain.com)‘

# Obey robots.txt rules
ROBOTSTXT_OBEY = True

# 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://doc.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://doc.scrapy.org/en/latest/topics/spider-middleware.html
#SPIDER_MIDDLEWARES = {
#    ‘myspider02.middlewares.Myspider02SpiderMiddleware‘: 543,
#}

# Enable or disable downloader middlewares
# See https://doc.scrapy.org/en/latest/topics/downloader-middleware.html
#DOWNLOADER_MIDDLEWARES = {
#    ‘myspider02.middlewares.Myspider02DownloaderMiddleware‘: 543,
#}

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

# Configure item pipelines
# See https://doc.scrapy.org/en/latest/topics/item-pipeline.html

#可以定义多个pipelines，数值代表执行的先后，数据越小越先经过这个管道
ITEM_PIPELINES = {
   ‘myspider02.pipelines.Myspider02Pipeline‘: 300,
   ‘myspider02.pipelines.Myspider02Pipeline1‘: 301,
}

# Enable and configure the AutoThrottle extension (disabled by default)
# See https://doc.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://doc.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‘