Python大数据之从网页上爬取数据的方法详解

#!/usr/bin/python
# -*- coding:utf-8 -*-
from scrapy.spiders import Spider
from lxml import etree
from jredu.items import JreduItem
class JreduSpider(Spider):
  name = 'tt' #爬虫的名字，必须的，唯一的
  allowed_domains = ['sohu.com']
  start_urls = [
    'http://www.sohu.com'
  ]
  def parse(self, response):
    content = response.body.decode('utf-8')
    dom = etree.HTML(content)
    for ul in dom.xpath("//div[@class='focus-news-box']/div[@class='list16']/ul"):
      lis = ul.xpath("./li")
      for li in lis:
        item = JreduItem() #定义对象
        if ul.index(li) == 0:
          strong = li.xpath("./a/strong/text()")
          li.xpath("./a/@href")
          item['title']= strong[0]
          item['href'] = li.xpath("./a/@href")[0]
        else:
          la = li.xpath("./a[last()]/text()")
          item['title'] = la[0]
          item['href'] = li.xpath("./a[last()]/href")[0]
        yield item

# -*- 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 JreduItem(scrapy.Item):#相当于Java里的实体类
  # define the fields for your item here like:
  # name = scrapy.Field()
  title = scrapy.Field()#创建一个field对象
  href = scrapy.Field()
  pass

# -*- coding: utf-8 -*-
# Define here the models for your spider middleware
#
# See documentation in:
# http://doc.scrapy.org/en/latest/topics/spider-middleware.html
from scrapy import signals
class JreduSpiderMiddleware(object):
  # Not all methods need to be defined. If a method is not defined,
  # scrapy acts as if the spider middleware does not modify the
  # passed objects.
  @classmethod
  def from_crawler(cls, crawler):
    # This method is used by Scrapy to create your spiders.
    s = cls()
    crawler.signals.connect(s.spider_opened, signal=signals.spider_opened)
    return s
  def process_spider_input(self, response, spider):
    # Called for each response that goes through the spider
    # middleware and into the spider.
    # Should return None or raise an exception.
    return None
  def process_spider_output(self, response, result, spider):
    # Called with the results returned from the Spider, after
    # it has processed the response.
    # Must return an iterable of Request, dict or Item objects.
    for i in result:
      yield i
  def process_spider_exception(self, response, exception, spider):
    # Called when a spider or process_spider_input() method
    # (from other spider middleware) raises an exception.
    # Should return either None or an iterable of Response, dict
    # or Item objects.
    pass
  def process_start_requests(self, start_requests, spider):
    # Called with the start requests of the spider, and works
    # similarly to the process_spider_output() method, except
    # that it doesn't have a response associated.
    # Must return only requests (not items).
    for r in start_requests:
      yield r
  def spider_opened(self, spider):
    spider.logger.info('Spider opened: %s' % spider.name)

# -*- 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
import codecs
import json
class JreduPipeline(object):
  def __init__(self):
    self.fill = codecs.open("data.txt",encoding="utf-8",mode="wb");
  def process_item(self, item, spider):
    line = json.dumps(dict(item))+"\n"
    self.fill.write(line)
    return item

# -*- coding: utf-8 -*-
# Scrapy settings for jredu 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 = 'jredu'
SPIDER_MODULES = ['jredu.spiders']
NEWSPIDER_MODULE = 'jredu.spiders'
# Crawl responsibly by identifying yourself (and your website) on the user-agent
#USER_AGENT = 'jredu (+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 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 = {
#  'jredu.middlewares.JreduSpiderMiddleware': 543,
#}
# Enable or disable downloader middlewares
# See http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
#DOWNLOADER_MIDDLEWARES = {
#  'jredu.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 = {
  'jredu.pipelines.JreduPipeline': 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'

#!/usr/bin/python
# -*- coding:utf-8 -*-
#爬虫文件的执行入口
from scrapy import cmdline
cmdline.execute("scrapy crawl tt".split())