web crawling(plus9) scrapy3

标签：disabled   ase   tor   throttle   topic   turn   utf-8   storage   print   

items:

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

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

import scrapy


class F1Item(scrapy.Item):
    # define the fields for your item here like:
    # name = scrapy.Field()
    content=scrapy.Field()
    link=scrapy.Field()


pipelines:

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

# Define your item pipelines here
#
# Don‘t forget to add your pipeline to the ITEM_PIPELINES setting
# See: http://doc.scrapy.org/en/latest/topics/item-pipeline.html


class F1Pipeline(object):
    def process_item(self, item, spider):
            for i in range(0,len(item("content"))):
                print(item["content"][i])
                print(item["link"][i])
                return item

setting:

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

# Scrapy settpings for f1 project
#
# For simplicity, this file contains only settings considered important or
# commonly used. You can find more settings consulting the documentation:
#
#     http://doc.scrapy.org/en/latest/topics/settings.html
#     http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
#     http://scrapy.readthedocs.org/en/latest/topics/spider-middleware.html

BOT_NAME = ‘f1‘

SPIDER_MODULES = [‘f1.spiders‘]
NEWSPIDER_MODULE = ‘f1.spiders‘


# Crawl responsibly by identifying yourself (and your website) on the user-agent
#USER_AGENT = ‘f1 (+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 http://scrapy.readthedocs.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 http://scrapy.readthedocs.org/en/latest/topics/spider-middleware.html
#SPIDER_MIDDLEWARES = {
#    ‘f1.middlewares.F1SpiderMiddleware‘: 543,
#}

# Enable or disable downloader middlewares
# See http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
#DOWNLOADER_MIDDLEWARES = {
#    ‘f1.middlewares.MyCustomDownloaderMiddleware‘: 543,
#}

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

# Configure item pipelines
# See http://scrapy.readthedocs.org/en/latest/topics/item-pipeline.html
ITEM_PIPELINES = {
   ‘f1.pipelines.F1Pipeline‘: 300,
}

# Enable and configure the AutoThrottle extension (disabled by default)
# See http://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 http://scrapy.readthedocs.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‘


spider:

# -*- coding: utf-8 -*-
import scrapy
from f1.items import F1Item
from scrapy.http import Request

class SpiderSpider(scrapy.Spider):
    name = ‘spider‘
    allowed_domains = [‘qiushibaike.com‘]

    def start_requests(self):
        usragent={"User-Agent","Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/60.0.3112.90 Safari/537.36Query String Parametersview sourceview URL encoded"}
        yield Request("https://www.qiushibaike.com/",headers=usragent)
    def parse(self, response):
        item=F1Item()
        item["content"]=response.xpath(‘//div[@class="content"]span/text()‘).extract()
        item["link"] = response.xpath(‘//a[@class="contentHerf"]/@href‘).extract()
        yield item



cmd:

E:\m\f1>scrapy crawl spider

web crawling(plus9) scrapy3

标签：disabled   ase   tor   throttle   topic   turn   utf-8   storage   print   

原文地址：http://www.cnblogs.com/rabbittail/p/7636993.html