Scrapy爬虫

import scrapy
from scrapy.loader import ItemLoader
from scrapy.loader.processors import TakeFirst


class StockstarItemLoader(ItemLoader):
    #自定义itemloader
    default_output_processor = TakeFirst()


class StockstarItem(scrapy.Item):
    # define the fields for your item here like:
    # name = scrapy.Field()
    code = scrapy.Field()  # 股票代码
    abbr = scrapy.Field()  # 股票简称

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

# Scrapy settings for stockstar 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

from scrapy.exporters import JsonLinesItemExporter

# 默认显示的中文是阅读性较差的Unicode字符
# 需要定义子类显示出原来的字符集(将父类的ensure_ascii属性设置为False即可)
class CustomJsonLinesItemExporter(JsonLinesItemExporter):
    def __init__(self, file, **kwargs):
        super(CustomJsonLinesItemExporter, self).__init__(file, ensure_ascii=False, **kwargs)

# 启用新定义的Exporter类
FEED_EXPORTERS = {
    ‘json‘: ‘stockstar.settings.CustomJsonLinesItemExporter‘,
}

BOT_NAME = ‘stockstar‘

SPIDER_MODULES = [‘stockstar.spiders‘]
NEWSPIDER_MODULE = ‘stockstar.spiders‘


# Crawl responsibly by identifying yourself (and your website) on the user-agent
#USER_AGENT = ‘stockstar (+http://www.yourdomain.com)‘

# Obey robots.txt rules
ROBOTSTXT_OBEY = False


# 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 = 0.25
# 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 = {
#    ‘stockstar.middlewares.StockstarSpiderMiddleware‘: 543,
#}

# Enable or disable downloader middlewares
# See http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
#DOWNLOADER_MIDDLEWARES = {
#    ‘stockstar.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 = {
#    ‘stockstar.pipelines.StockstarPipeline‘: 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‘

# -*- coding: utf-8 -*-
import scrapy
from items import StockstarItem, StockstarItemLoader


class StockSpider(scrapy.Spider):
    name = ‘stock‘
    allowed_domains = [‘quote.stockstar.com‘]
    start_urls = [‘http://quote.stockstar.com/stock/ranklist_a_3_1_1.html‘]

    def parse(self, response):
        page = int(response.url.split("_")[-1].split(".")[0])
        item_nodes = response.css(‘#datalist tr‘)

        for item_node in item_nodes:
            item_loader = StockstarItemLoader(item=StockstarItem(), selector=item_node)
            item_loader.add_css("code", "td:nth-child(1) a::text")
            item_loader.add_css("abbr", "td:nth-child(2) a::text")
            yield stock_item

        if item_nodes:
            next_page = page + 1
            next_url = response.url.replace("{0}.html".format(page), "{0}.html".format(next_page))
            yield scrapy.Request(url=next_url, callback=self.parse)    

from scrapy.cmdline import execute

execute(["scrapy", "crawl", "stock", "-o", "items.json"])