Scrapy框架实战（12306余票）

发布于 2020-06-01  95 次阅读

Spider.py

# -*- coding: utf-8 -*-
import scrapy
import requests
import json
from ticket.items import TicketItem
from selenium import webdriver


class A12306SpiderSpider(scrapy.Spider):
    name = '12306_spider'
    allowed_domains = ['12306.cn']
    start_urls = [
        'https://kyfw.12306.cn/otn/leftTicket/init?linktypeid=dc&fs=%E5%8D%97%E5%AE%81,NNZ&ts=%E7%99%BE%E8%89%B2,BIZ&date=2020-06-02&flag=N,N,Y','https://kyfw.12306.cn/otn/leftTicket/query?leftTicketDTO.train_date=2020-06-02&leftTicketDTO.from_station=NNZ&leftTicketDTO.to_station=BIZ&purpose_codes=ADULT']
    headers={'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/83.0.4103.61 Safari/537.36 Edg/83.0.478.37'}
    def start_requests(self):
        url='https://kyfw.12306.cn/otn/leftTicket/init?linktypeid=dc&fs=%E7%99%BE%E8%89%B2,BIZ&ts=%E5%8D%97%E5%AE%81,NNZ&date=2020-06-02&flag=N,N,Y'
        req=scrapy.Request(url=url,headers=self.headers,callback=self.get_cookie,meta={'cookiejar':1})
        yield req

    def get_cookie(self, response):
        url='https://kyfw.12306.cn/otn/leftTicket/query?leftTicketDTO.train_date=2020-06-02&leftTicketDTO.from_station=BIZ&leftTicketDTO.to_station=NNZ&purpose_codes=ADULT'
        req=scrapy.Request(url=url,meta={'cookiejar':response.meta['cookiejar']},headers=self.headers,callback=self.get_train_info)
        yield req

    def get_train_info(self,response):
        text =response.body.decode('UTF-8')
        text=json.loads(text)
        result = text['data']['result']
        print(result)
        for i in result:
            item = i.split('|')
            train_code = item[3]
            train_start_time = item[8]
            train_end_time = item[9]
            sit_1 = item[31]
            sit_2 = item[30]
            items = TicketItem(train_code=train_code, train_start_time=train_start_time, train_end_time=train_end_time,
                               sit_1=sit_1, sit_2=sit_2)
            yield items

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 random
from scrapy.exporters import JsonLinesItemExporter,JsonItemExporter,CsvItemExporter
class TicketPipeline:
    def __init__(self):
        self.fp=open('ticket.json','wb')
        self.exporter=JsonLinesItemExporter(self.fp,ensure_ascii=False)
    def start_spider(self):
        self.exporter.start_exporting()

    def process_item(self, item, spider):
        self.exporter.export_item(item)

    def close_item(self):
        self.fp.close()
  • 储存器中间件用的是json数据格式保存数据

settings.py

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

# Scrapy settings for ticket project
#
# For simplicity, this file contains only settings considered important or
# commonly used. You can find more settings consulting the documentation:
#
#     https://docs.scrapy.org/en/latest/topics/settings.html
#     https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
#     https://docs.scrapy.org/en/latest/topics/spider-middleware.html

BOT_NAME = 'ticket'

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


# Crawl responsibly by identifying yourself (and your website) on the user-agent
#USER_AGENT = 'ticket (+http://www.yourdomain.com)'
from fake_useragent import UserAgent
import random
# 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 https://docs.scrapy.org/en/latest/topics/settings.html#download-delay
# See also autothrottle settings and docs
#DOWNLOAD_DELAY = 3
# 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 = True

# 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',
  'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/83.0.4103.61 Safari/537.36 Edg/83.0.478.37'
}

# Enable or disable spider middlewares
# See https://docs.scrapy.org/en/latest/topics/spider-middleware.html
#SPIDER_MIDDLEWARES = {
#    'ticket.middlewares.TicketSpiderMiddleware': 543,
#}

# Enable or disable downloader middlewares
# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
#DOWNLOADER_MIDDLEWARES = {
#    'ticket.middlewares.TicketDownloaderMiddleware': 543,
#}

# Enable or disable extensions
# See https://docs.scrapy.org/en/latest/topics/extensions.html
#EXTENSIONS = {
#    'scrapy.extensions.telnet.TelnetConsole': None,
#}

# Configure item pipelines
# See https://docs.scrapy.org/en/latest/topics/item-pipeline.html
ITEM_PIPELINES = {
   'ticket.pipelines.TicketPipeline': 300,
}

# Enable and configure the AutoThrottle extension (disabled by default)
# See https://docs.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 https://docs.scrapy.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'

setting只要注意header的设置就行

初闻天籁之音，未使心之将来
未来可期