投诉网站爬虫

 1 # -*- coding: utf-8 -*-
 2 import scrapy
 3 from yg.items import YgItem
 4 
 5 class YgSpiderSpider(scrapy.Spider):
 6     name = 'yg_spider'
 7     allowed_domains = ['wz.sun0769.com']
 8     start_urls = ['http://wz.sun0769.com/index.php/question/questionType?type=4&page=0']
 9 
10     def parse(self, response):
11         tr_list = response.xpath("//div[@class='greyframe']/table[2]/tr/td/table/tr")
12         for tr in tr_list:
13             item = YgItem()
14             item["title"] = tr.xpath("./td[2]/a[2]/@title").extract_first()
15             item["href"] = tr.xpath("./td[2]/a[2]/@href").extract_first()
16             item["update_time"] = tr.xpath("./td[last()]/text()").extract_first()
17             # print(item)
18 
19             yield scrapy.Request(
20                 item["href"],
21                 callback=self.parse_detail,
22                 meta={"item":item}
23             )
24 
25         next_url = response.xpath("//a[text()='>']/@href").extract_first()
26         if next_url is not None:
27             yield scrapy.Request(
28                 next_url,
29                 callback=self.parse
30             )
31 
32     def parse_detail(self,response): #处理详情页
33         item = response.meta["item"]
34         item["content"] = response.xpath("//div[@class='c1 text14_2']//text()").extract()
35         item["content_img"] = response.xpath("//div[@class='c1 text14_2']//img/@src").extract()
36         item["content_img"] = ["http://wz.sun0769.com"+i for i in item["content_img"]]
37         # print(item)
38         yield item

 1 # -*- coding: utf-8 -*-
 2 
 3 # Define your item pipelines here
 4 #
 5 # Don't forget to add your pipeline to the ITEM_PIPELINES setting
 6 # See: https://doc.scrapy.org/en/latest/topics/item-pipeline.html
 7 import re
 8 import json
 9 
10 class YgPipeline(object):
11     def process_item(self, item, spider):
12         item["content"] = self.process_content(item["content"])
13         with open("yg.txt", "a", encoding="utf-8") as f:
14             f.write(json.dumps(dict(item), ensure_ascii=False, indent=4))
15             f.write("\n")
16         return item
17 
18     def process_content(self, content):
19         content = [re.sub(r'\xa0|\s',"",i) for i in content]
20         content = [i for i in content if len(i)>0]
21         return content

 1 # -*- coding: utf-8 -*-
 2 
 3 # Define here the models for your scraped items
 4 #
 5 # See documentation in:
 6 # https://doc.scrapy.org/en/latest/topics/items.html
 7 
 8 import scrapy
 9 
10 
11 class YgItem(scrapy.Item):
12     # define the fields for your item here like:
13     title = scrapy.Field()
14     update_time = scrapy.Field()
15     href = scrapy.Field()
16     content = scrapy.Field()
17     content_img = scrapy.Field()
18     # pass

猜你喜欢