Python:阳光热线问政平台爬虫

爬取投诉帖子的编号、帖子的url、帖子的标题，和帖子里的内容。

items.py

import scrapy

class DongguanItem(scrapy.Item):
# 每个帖子的标题
title = scrapy.Field()
# 每个帖子的编号
number = scrapy.Field()
# 每个帖子的文字内容
content = scrapy.Field()
# 每个帖子的url
url = scrapy.Field()

spiders/sunwz.py

Spider 版本

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

import scrapy
from dongguan.items import DongguanItem

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

def parse(self, response):
# 取出每个页面里帖子链接列表
links = response.xpath("//div[@class='greyframe']/table//td/a[@class='news14']/@href").extract()
# 迭代发送每个帖子的请求，调用parse_item方法处理
for link in links:
yield scrapy.Request(link, callback = self.parse_item)
# 设置页码终止条件，并且每次发送新的页面请求调用parse方法处理
if self.offset <= 71130:
self.offset += 30
yield scrapy.Request(self.url + str(self.offset), callback = self.parse)

# 处理每个帖子里
def parse_item(self, response):
item = DongguanItem()
# 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]

# 文字内容，默认先取出有图片情况下的文字内容列表
content = response.xpath('//div[@class="contentext"]/text()').extract()
# 如果没有内容，则取出没有图片情况下的文字内容列表
if len(content) == 0:
content = response.xpath('//div[@class="c1 text14_2"]/text()').extract()
# content为列表，通过join方法拼接为字符串，并去除首尾空格
item['content'] = "".join(content).strip()
else:
item['content'] = "".join(content).strip()

# 链接
item['url'] = response.url

yield item

CrawlSpider 版本

# -*- coding: utf-8 -*-
import scrapy
from scrapy.linkextractors import LinkExtractor
from scrapy.spiders import CrawlSpider, Rule
from dongguan.items import DongguanItem
import time


class SunSpider(CrawlSpider):
name = 'sun'
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'))
# 每个帖子的匹配规则
contentlink = LinkExtractor(allow=r'/html/question/\d+/\d+.shtml')

rules = [
# 本案例为特殊情况，需要调用deal_links方法处理每个页面里的链接
Rule(pagelink, process_links = "deal_links", follow = True),
Rule(contentlink, callback = 'parse_item')
]

# 需要重新处理每个页面里的链接，将链接里的‘Type&type=4?page=xxx’替换为‘Type?type=4&page=xxx’（或者是Type&page=xxx?type=4’替换为‘Type?page=xxx&type=4’），否则无法发送这个链接
def deal_links(self, links):
for link in links:
link.url = link.url.replace("?","&").replace("Type&", "Type?")
print link.url
return links


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

# 文字内容，默认先取出有图片情况下的文字内容列表
content = response.xpath('//div[@class="contentext"]/text()').extract()
# 如果没有内容，则取出没有图片情况下的文字内容列表
if len(content) == 0:
content = response.xpath('//div[@class="c1 text14_2"]/text()').extract()
# content为列表，通过join方法拼接为字符串，并去除首尾空格
item['content'] = "".join(content).strip()
else:
item['content'] = "".join(content).strip()

# 链接
item['url'] = response.url

yield item

pipelines.py

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

# 文件处理类库，可以指定编码格式
import codecs
import json

class JsonWriterPipeline(object):

def __init__(self):
# 创建一个只写文件，指定文本编码格式为utf-8
self.filename = codecs.open('sunwz.json', 'w', encoding='utf-8')

def process_item(self, item, spider):
content = json.dumps(dict(item), ensure_ascii=False) + "\n"
self.filename.write(content)
return item

def spider_closed(self, spider):
self.file.close()

settings.py

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

# 日志文件名和处理等级
LOG_FILE = "dg.log"
LOG_LEVEL = "DEBUG"

在项目根目录下新建main.py文件,用于调试

from scrapy import cmdline
cmdline.execute('scrapy crawl sunwz'.split())

执行程序

py2 main.py