scrapy爬取珍爱网数据

main.py

from scrapy import cmdline
cmdline.execute(['scrapy','crawl','zhenai'])

settings.py

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

# Scrapy settings for zhenaiwang 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 = 'zhenaiwang'

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


# Crawl responsibly by identifying yourself (and your website) on the user-agent
#USER_AGENT = 'zhenaiwang (+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 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 = 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 https://docs.scrapy.org/en/latest/topics/spider-middleware.html
#SPIDER_MIDDLEWARES = {
#    'zhenaiwang.middlewares.ZhenaiwangSpiderMiddleware': 543,
#}

# Enable or disable downloader middlewares
# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
#DOWNLOADER_MIDDLEWARES = {
#    'zhenaiwang.middlewares.ZhenaiwangDownloaderMiddleware': 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 = {
   'zhenaiwang.pipelines.ZhenaiwangPipeline': 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'

items.py

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

# Define here the models for your scraped items
#
# See documentation in:
# https://docs.scrapy.org/en/latest/topics/items.html

import scrapy


class ZhenaiwangItem(scrapy.Item):
    # define the fields for your item here like:

    name = scrapy.Field()
    age = scrapy.Field()
    local = scrapy.Field()
    sex = scrapy.Field()
    status = scrapy.Field()
    height = scrapy.Field()
    education = 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 MySQLdb

conn = MySQLdb.connect(
    host = 'localhost',
    port = 3306,
    user = 'root',
    password = '123456',
    db = 'spider',
    charset = 'utf8'
)

cursor = conn.cursor()

class ZhenaiwangPipeline(object):
    def process_item(self, item, spider):
        sql = 'insert into t_zhenai values (%s,%s,%s,%s,%s,%s,%s)'
        data = (item['name'],item['age'],item['local'],item['sex'],item['status'],item['height'],item['education'])
        cursor.execute(sql,data)
        conn.commit()

        return item

zhenai_spider.py

import scrapy
from ..items import ZhenaiwangItem

headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/74.0.3729.131 Safari/537.36',
    'Cookie': 'sid=650e6f9b-337e-4f79-aa1d-e0e18073c2d1; Hm_lvt_2c8ad67df9e787ad29dbd54ee608f5d2=1572424230; __channelId=905819%2C0; oneclickLoginSwitch=2897; oneClickRegisterSwitch=2783; Hm_lpvt_2c8ad67df9e787ad29dbd54ee608f5d2=1572425293',
    'Host': 'www.zhenai.com',
}

class ZhenaiSpider(scrapy.Spider):
    name = 'zhenai'

    def start_requests(self):
        url = 'http://www.zhenai.com/zhenghun/'
        yield scrapy.Request(url=url)

    def parse(self, response):
        urls = response.xpath('//*[@id="app"]/article/dl/dd/a/@href').getall()
        for url in urls:
            #获取6页数据
            for i in range(1,7):
                url = url + '/' +str(i)
                yield scrapy.Request(url=url,headers=headers,callback=self.parse1)

    def parse1(self, response):
        name = response.xpath('//table/tbody/tr[1]/th/a/text()').getall()

        # sex = response.xpath('//table/tbody/tr[2]/td[1]').xpath('string(.)').getall()
        sex = response.xpath('//table/tbody/tr[2]/td[1]/text()').getall()
        local = response.xpath('//table/tbody/tr[2]/td[2]/text()').getall()
        # local = response.xpath('//table/tbody/tr[2]/td[2]').xpath('string(.)').getall()

        # age = response.xpath('//table/tbody/tr[3]/td[1]').xpath('string(.)').getall()
        age = response.xpath('//table/tbody/tr[3]/td[1]/text()').getall()
        education = response.xpath('//table/tbody/tr[3]/td[2]/text()').getall()
        # education = response.xpath('//table/tbody/tr[3]/td[2]').xpath('string(.)').getall()

        # status = response.xpath('//table/tbody/tr[4]/td[1]').xpath('string(.)').getall()
        status = response.xpath('//table/tbody/tr[4]/td[1]/text()').getall()
        height = response.xpath('//table/tbody/tr[4]/td[2]/text()').getall()
        # height = response.xpath('//table/tbody/tr[4]/td[2]').xpath('string(.)').getall()
        print(name,age,local,sex,status,height,education)

        print(len(sex),len(name),len(age),len(local),len(status),len(height),len(education))


        for i in range(len(name)):
            info = ZhenaiwangItem()
            #对info字典进行赋值
            info['name'] = name[i]
            info['age'] = age[i]
            info['local'] = local[i]
            info['sex'] = sex[i]
            info['status'] = status[i]
            info['height'] = height[i]
            info['education'] = education[i]
            yield info