贪心学院 scrapy爬虫

生成爬虫

scrapy genspider 爬虫名 网址

打开调试用shell

scrapy shell 网址

主体 stock.py

# -*- coding: utf-8 -*-
import re
from urllib import parse
import scrapy
from stock_spider.items import StockItem

class StockSpider(scrapy.Spider):
    name = 'stock'
    allowed_domains = ['pycs.greedyai.com/']  #域名
    start_urls = ['http://pycs.greedyai.com/']    #地址

    def parse(self, response):
        post_urls= response.xpath("//a/@href").extract()  #获取子网址
        for post_url in post_urls:
            yield scrapy.Request(url=parse.urljoin(response.url,post_url),callback=self.parse_detail,dont_filter=True)  #整合成可访问的网址

    def parse_detail(self,response):
        stock_item= StockItem()
        #董事会成员
        stock_item['names']=self.get_name(response)

        #性别
        # stock_item['sexs']=self.get_sex(response)  #部分人员无性别资料导致后来的list越界

        #股票代码
        stock_item['codes']=self.get_code(response)

        #成员职位
        stock_item['positions']=self.get_position(response)
        yield stock_item

    def get_name(self,response):
        name=response.xpath("//td[@class=\"tc name\"]/a/text()").extract()
        return name

    def get_sex(self,response):
        sex_temp = response.xpath("//td[@class=\"intro\"]/text()").extract()
        sex_list=[]
        for sex_info in sex_temp:
            try:
                sex=re.findall("男|女",sex_info)[0]
                sex_list.append(sex)
            except(IndexError):  #捕获到该异常，则继续往下读取，因为视频上显示在有用数据前后有一些无效的转义字符
                continue
        return sex_list

    def get_code(self,response):
        code_temp=response.xpath("/html/body/div[3]/div[1]/div[2]/div[1]/h1/a/@title").extract()
        for code_info in code_temp:
            code=re.findall("\d+",code_info)
        return code

    def get_position(self,response):
        position = response.xpath("//td[@class=\"tl\"]/text()").extract()
        return position

main.py

from scrapy.cmdline import execute  #调试用

import sys
import os

sys.path.append(os.path.dirname(os.path.abspath(__file__)))
execute(["scrapy","crawl","stock"])

items.py

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

import scrapy

class StockSpiderItem(scrapy.Item):
    # define the fields for your item here like:
    # name = scrapy.Field()
    pass

class StockItem(scrapy.Item):  #新添加
    names=scrapy.Field()
    # sexs=scrapy.Field()
    codes=scrapy.Field()
    positions=scrapy.Field()

pipelines.py

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

# Define your item pipelines here
#
# Don't forget to add your pipeline to the ITEM_PIPELINES setting
# See: https://docs.scrapy.org/en/latest/topics/item-pipeline.html

import os

class StockSpiderPipeline(object):
    def process_item(self, item, spider):
        return item

class StockPipeline(object): #新添加

    # 类被加载时创建一个文件
    def __init__(self):
        self.file=open("executive_prep.csv","a+") # a+有则追加，无则创建

    def process_item(self, item, spider):

        #判断文件是否为空，为空则写入标头：姓名,性别,股票代码,职位
        #为空则追加写文件
        if os.path.getsize("executive_prep.csv"): #获取文件大小
            #开始写文件
            self.write_content(item)
        else:
            self.file.write("姓名,性别,股票代码,职位\n")
        self.file.flush()

    def write_content(self,item):

        names = item['names']
        # sexs = item['sexs']
        codes = item['codes']
        positions = item['positions']
        for i in range(len(names)):
            result=names[i]+","+codes[0]+","+positions[i]+"\n"
            self.file.write(result)

settings.py

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

BOT_NAME = 'stock_spider'

SPIDER_MODULES = ['stock_spider.spiders']
NEWSPIDER_MODULE = 'stock_spider.spiders' #新添加

# Configure item pipelines
# See https://docs.scrapy.org/en/latest/topics/item-pipeline.html
ITEM_PIPELINES = {
   'stock_spider.pipelines.StockSpiderPipeline': 300,
    'stock_spider.pipelines.StockPipeline': 300, #新添加
}