python爬虫之scrapy

环境：centos6 + python3
安装：pip3 install scrapy
报错：src/twisted/test/raiser.c:4:20: error: Python.h: No such file or directory
    src/twisted/test/raiser.c:6:6: error: #error Python headers needed to compile C extensions, please install development version of Python.
    error: command 'gcc' failed with exit status 1
解决：需要安装Python的头文件和静态库包(python-devel)
yum search python3 | grep devel #搜索python3下的devel
yum install -y python34-devel.x86_64#安装python34-devel.x86_64 

pip3 install scrapy#成功 

1、创建项目
cd /home/chaoge/mypython/crawler/

scrapy startproject myscrapy

vi items.py

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

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

import scrapy


class MyscrapyItem(scrapy.Item):
    # define the fields for your item here like:
    #职位名称
    positionName = scrapy.Field()
    #职位连接
    positionLink = scrapy.Field()
    #职位类型
    positionType = scrapy.Field()
    #招聘人数
    peopleNum = scrapy.Field()
    #工作地点
    workLocation = scrapy.Field()
    #发布时间
    publishTime = scrapy.Field()

vi pipelines.py

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

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

class MyscrapyPipeline(object):
    def __init__(self):
        self.filename = open("tencent.json","wb")

    def process_item(self, item, spider):
        text = json.dumps(dict(item),ensure_ascii=False)+"
"
        self.filename.write(text.encode("utf-8"))
        return item
    
    def close_spider(self,spider):
        self.filename.close()

vi settings.py 

# Override the default request headers:
DEFAULT_REQUEST_HEADERS = { 
    'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.108 Safari/537.36',  
    'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
#   'Accept-Language': 'en',
}

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

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

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

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

2、创建基础类
cd myscrapy/myscrapy/spiders

scrapy genspider tencent "tencent.com"

vi tencent.py 

# -*- coding: utf-8 -*-
import scrapy
from myscrapy.items import MyscrapyItem


class TencentSpider(scrapy.Spider):
    name = 'tencent'
    allowed_domains = ['tencent.com']
    url = "http://hr.tencent.com/position.php?&start="
    offset=0
    #start_urls = ['http://tencent.com/']
    start_urls = [url+str(offset)]
    def parse(self, response):
        for each in response.xpath("//tr[@class='even']|//tr[@class='odd']"):
            #初始化模型对象
            item = MyscrapyItem()

            #职位名称
            item['positionName'] = each.xpath("./td[1]/a/text()").extract()[0]
            #职位连接
            item['positionLink'] = each.xpath("./td[1]/a/@href").extract()[0]
            #职位类型
            item['positionType'] = each.xpath("./td[2]/text()").extract()[0]
            #招聘人数
            item['peopleNum'] = each.xpath("./td[3]/text()").extract()[0]
            #工作地点
            item['workLocation'] = each.xpath("./td[4]/text()").extract()[0]
            #发布时间
            item['publishTime'] = each.xpath("./td[5]/text()").extract()[0]

            #将数据交给管道文件处理
            yield item

        if self.offset < 50:
            self.offset += 10
            #将请求重新发送给调度器，入队列，出队列，交给下载器下载
            yield scrapy.Request(self.url + str(self.offset),callback = self.parse)
        else:
            print("end.")

3、执行

scrapy crawl tencent

模拟登陆

# -*- coding: utf-8 -*-
import scrapy


class RenrenspiderSpider(scrapy.Spider):
    name = 'renrenspider'
    allowed_domains = ['renren.com']
    #start_urls = ['http://renren.com/']

    def start_requests(self):
        url = 'http://www.renren.com/PLogin.do'
        yield scrapy.FormRequest(url = url, formdata={"email":"XXXX@163.com","password":"XXXXXX"},callback=self.parse_page)
    def parse_page(self, response):
        with open("info.html","wb") as filename:
            filename.write(response.body)

下载图片：

运行时报错： File "/usr/lib64/python3.4/site-packages/scrapy/pipelines/images.py", line 15, in <module>
    from PIL import Image
ImportError: No module named 'PIL'
解决办法：pip3 install pillow
vi items.py

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

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

import scrapy


class DouyuItem(scrapy.Item):
    # define the fields for your item here like:
    nickname = scrapy.Field()
    imagelink = scrapy.Field()
    imagepath = scrapy.Field()

vi pipelines.py 

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

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

import scrapy
from scrapy.utils.project import get_project_settings
from scrapy.pipelines.images import ImagesPipeline
import json
import os

class DouyuPipeline(ImagesPipeline):
    #获取settings中的常量
    IMAGES_STORE = get_project_settings().get('IMAGES_STORE')
    def get_media_requests(self, item, info):
        image_url = item['imagelink'] 
        yield scrapy.Request(image_url)

    def item_completed(self, results, item, info):
        print(results)
        #exit(1)
        image_path = [x['path'] for ok, x in results if ok]
        os.rename(self.IMAGES_STORE+"/"+image_path[0],self.IMAGES_STORE+"/"+item['nickname']+".jpg")
        item['imagepath'] = self.IMAGES_STORE+"/"+item['nickname']
        return item

vi spiders/douyuavatar.py

# -*- coding: utf-8 -*-
import scrapy
from douyu.items import DouyuItem
import json

class DouyuavatarSpider(scrapy.Spider):
    name = 'douyuavatar'
    allowed_domains = ['capi.douyucdn.cn']
    url = "http://capi.douyucdn.cn/api/v1/getVerticalRoom?limit=20&offset="
    offset=0
    #start_urls = ['http://tencent.com/']
    start_urls = [url+str(offset)]
    def parse(self, response):
        #把json转换为python格式
        data = json.loads(response.text)['data']
        #print(data)
        #exit(1)
        for value in data:
            item = DouyuItem()
            item['nickname'] = value['nickname']
            item['imagelink'] = value['vertical_src']
            yield item
        if self.offset < 50:    
            self.offset += 20
            yield scrapy.Request(self.url + str(self.offset), callback = self.parse)