scrapy---简介 、（爬取赶集）

创建scrapy文件

C:\Users\dell\PycharmProjects\TestDemo001\TestDemo001>scrapy startproject TestDemo001

scrapy genspider -t basic ganji "http://anqing.ganji.com/"

scrapy crawl ganji

存储csv

scrapy crawl ganji -o ganji.csv

爬赶集

ganji.py

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

from TestDemo001.items import Testdemo001Item


class GanjiSpider(scrapy.Spider):
    name = 'ganji'
    allowed_domains = ['http://anqing.ganji.com/']
    start_urls = []
    start_url = 'http://bj.ganji.com/site/s/f0/_%E7%A8%8B%E5%BA%8F%E5%91%98/'
    for i in range(0,1985,32):
        start_urls.append(start_url.replace("f0","f"+str(i)))

    def parse(self, response):
        node_list = response.xpath("//div[@class='job-wanted']/dl")
        for node in node_list:
            try:
                ti = Testdemo001Item()
                name = node.xpath("./dt[@class='f-introd']/a/text()").extract()[0]
                addr = node.xpath("./dd[@class='addr']/a/text()").extract()[0]
                time = node.xpath("./dd[@class='j-time']/text()").extract()[0]
                ti["name"] = name
                ti["addr"] = addr
                ti["time"] = time
                yield ti
            except:
                pass

item.py

import scrapy


class Testdemo001Item(scrapy.Item):
    # define the fields for your item here like:
    name = scrapy.Field()
    addr = scrapy.Field()
    time = scrapy.Field()

pipelines.py

class Testdemo001Pipeline(object):
    def process_item(self, item, spider):
       # with open("text.txt","w+") as f:
            #f.write(item)
        if item ==None:
            return None
        else:
            with open("text.txt","a+") as f:
                f.write(item["name"]+item["addr"]+item["time"]+"\n")
            return item

settings.py

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

# Scrapy settings for TestDemo001 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 = 'TestDemo001'

SPIDER_MODULES = ['TestDemo001.spiders']
NEWSPIDER_MODULE = 'TestDemo001.spiders'


# Crawl responsibly by identifying yourself (and your website) on the user-agent
#USER_AGENT = 'TestDemo001 (+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://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 = {
#    'TestDemo001.middlewares.Testdemo001SpiderMiddleware': 543,
#}

# Enable or disable downloader middlewares
# See https://doc.scrapy.org/en/latest/topics/downloader-middleware.html
#DOWNLOADER_MIDDLEWARES = {
#    'TestDemo001.middlewares.Testdemo001DownloaderMiddleware': 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
ITEM_PIPELINES = {
    'TestDemo001.pipelines.Testdemo001Pipeline': 300,
}

# 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'