爬取阳光问政平台

创建项目

scrapy startproject dongguan

items.py

import scrapy


class DongguanItem(scrapy.Item):
    # define the fields for your item here like:
    title = scrapy.Field()
    content = scrapy.Field()
    url = scrapy.Field()
    number = scrapy.Field()

创建CrawSpider，使用模版crawl

scrapy genspider -t crawl sun wz.sun0769.com

 

sun.py

import scrapy
from scrapy.linkextractors import LinkExtractor
from scrapy.spiders import CrawlSpider, Rule
from dongguan.items import DongguanItem

class SunSpider(CrawlSpider):
    name = 'sun'
    allowed_domains = ['wz.sun0769.com']
    start_urls = ['http://wz.sun0769.com/index.php/question/questionType?type=4&page=0']

    rules = (
        Rule(LinkExtractor(allow=r'type=4&page=\d+')),
        Rule(LinkExtractor(allow=r'/html/question/\d+/\d+.shtml'), callback = 'parse_item'),
    )

    def parse_item(self, response):
        item = DongguanItem()

        item['title'] = response.xpath('//div[contains(@class, "pagecenter p3")]//strong/text()').extract()[0]
        # 编号
        item['number'] = item['title'].split(' ')[-1].split(":")[-1]
        # 内容
        item['content'] = response.xpath('//div[@class="c1 text14_2"]/text()').extract()[0]
        # 链接
        item['url'] = response.url

        yield item

 

pipelines.py

import json

class DongguanPipeline(object):
    def __init__(self):
        self.filename = open("dongguan.json", "w")

    def process_item(self, item, spider):
        text = json.dumps(dict(item), ensure_ascii = False) + ",\n"
        self.filename.write(text.encode("utf-8"))
        #python3中需改为：self.filename.write(text)

　　　　　return item 

　　 def close_spider(self, spider): 
   　　  self.filename.close()

settings.py

BOT_NAME = 'dongguan'

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

ROBOTSTXT_OBEY = True

ITEM_PIPELINES = {
    'dongguan.pipelines.DongguanPipeline': 300,
}

LOG_FILE = "dg.log"
LOG_LEVEL = "DEBUG"

 

 执行

scrapy crawl sun

发现爬取内容有缺失

问题分析：

通过 print(response.url)分析：

import scrapy
from scrapy.linkextractors import LinkExtractor
from scrapy.spiders import CrawlSpider, Rule
from dongguan.items import DongguanItem

class SunSpider(CrawlSpider):
    name = 'sun'
    allowed_domains = ['wz.sun0769.com']
    start_urls = ['http://wz.sun0769.com/index.php/question/questionType?type=4&page=0']

    rules = (
        Rule(LinkExtractor(allow=r'type=4&page=\d+'),callback = 'parse_item'),
        #Rule(LinkExtractor(allow=r'/html/question/\d+/\d+.shtml'), callback = 'parse_item'),
    )

    def parse_item(self, response):
        print(response.url)
        '''
        item = DongguanItem()

        item['title'] = response.xpath('//div[contains(@class, "pagecenter p3")]//strong/text()').extract()[0]
        # 编号
        item['number'] = item['title'].split(' ')[-1].split(":")[-1]
        # 内容
        item['content'] = response.xpath('//div[@class="c1 text14_2"]/text()').extract()[0]
        # 链接
        item['url'] = response.url

        yield item
        ''' 

 更改匹配规则：

    rules = (
        Rule(LinkExtractor(allow=r'type=4'),callback = 'parse_item'),
    ) 

 

设置

follow=True

修改sun.py 

 

 响应内容不一定是发送的url，后面的URL无效。

改写sun.py

import scrapy
from scrapy.linkextractors import LinkExtractor
from scrapy.spiders import CrawlSpider, Rule
from newdongguan.items import NewdongguanItem

class DongdongSpider(CrawlSpider):
    name = 'dongdong'
    allowed_domains = ['wz.sun0769.com']
    start_urls = ['http://wz.sun0769.com/index.php/question/questionType?type=4&page=']

    # 每一页的匹配规则
    pagelink = LinkExtractor(allow=("type=4"))
    # 每一页里的每个帖子的匹配规则
    contentlink = LinkExtractor(allow=(r"/html/question/\d+/\d+.shtml"))

    rules = (
        # 本案例的url被web服务器篡改，需要调用process_links来处理提取出来的url
        Rule(pagelink, process_links = "deal_links"),
        Rule(contentlink, callback = "parse_item")
    )

    # links 是当前response里提取出来的链接列表
    def deal_links(self, links):
        for each in links:
            each.url = each.url.replace("?","&").replace("Type&","Type?")
        return links

    def parse_item(self, response):
        item = NewdongguanItem()
        # 标题
        item['title'] = response.xpath('//div[contains(@class, "pagecenter p3")]//strong/text()').extract()[0]
        # 编号
        item['number'] = item['title'].split(' ')[-1].split(":")[-1]
        # 内容，先使用有图片情况下的匹配规则，如果有内容，返回所有内容的列表集合
        content = response.xpath('//div[@class="contentext"]/text()').extract()
        # 如果没有内容，则返回空列表，则使用无图片情况下的匹配规则
        if len(content) == 0:
            content = response.xpath('//div[@class="c1 text14_2"]/text()').extract()
            item['content'] = "".join(content).strip()
        else:
            item['content'] = "".join(content).strip()
        # 链接
        item['url'] = response.url

        yield item