学习笔记：scrapy框架初探

Scrapy是: 由Python语言开发的一个快速、高层次的屏幕抓取和web抓取框架，用于抓取web站点并从页面中提取结构化的数据。

Scrapy用途广泛，可以用于数据挖掘、监测和自动化测试

Scrapy指令：

创建项目：scrapy startproject xxx（工程名）

进入项目：cd xxx #进入某个文件夹下

创建爬虫：scrapy genspider xxx（爬虫名） xxx.com （爬取域）

运行爬虫：scrapy crawl XXX（爬虫名）

列出所有爬虫：scrapy list

生成文件：scrapy crawl xxx -o xxx.json (生成某种类型的文件)

爬虫文件：

（1）spiders文件夹：存放爬虫文件的文件夹。

（2）items.py：定义需要抓取的数据。

（3）pipelines.py：负责数据抓取以后的处理工作。

（4）settings.py：爬虫的各种配置信息。

dmoz.py

import scrapy
class DmozSpider(scrapy.Spider): # 继承Spider类
    name = "dmoz" # 爬虫的唯一标识，不能重复，启动爬虫的时候要用
    allowed_domains = ["dmoz.org"] # 限定域名，只爬取该域名下的网页
    start_urls = [ # 开始爬取的链接
        "https://www.baidu.com/"
    ]
    def parse(self, response):
        title=response.xpath('//title/text()').extract()
        tit=response.xpath('//title/text()').re('\w')
        print(tit)

创建main.py才可以在pycharm中运行
main.py

from scrapy import cmdline
cmdline.execute("scrapy crawl example".split())

setting.py改掉君子协议

# Obey robots.txt rules
ROBOTSTXT_OBEY = False

在dmoz.py文件中存储数据：通过item

from (工程名).items import （items.py中的class名字)

item =（items.py中的class名字）
item['phone'] = person_info[3]
yield item

例子：

from baidu.items import PersonInfoItem
item = PersonInfoItem()
person_info = person.xpath('td/text()').extract()
item['name'] = person_info[0]
item['age'] = person_info[1]
item['salary'] = person_info[2]
item['phone'] = person_info[3]
yield item

在items.py中：

class 名字(scrapy.Item):
    name = scrapy.Field()
    

往数据库中存储数据：

setting.py加入

MONGODB_HOST = '127.0.0.1'
MONGODB_PORT = 27017
MONGODB_DBNAME = 'blogspider'
MONGODB_DOCNAME = 'blog'

pipelines.py

import pymongo
from scrapy.utils.project import get_project_settings
settings = get_project_settings()

class TutorialPipeline:
    def __init__(self):
        host = settings['MONGODB_HOST']
        port = settings['MONGODB_PORT']
        db_name = settings['MONGODB_DBNAME']
        client = pymongo.MongoClient(host=host, port=port)
        db = client[db_name]
        self.post = db[settings['MONGODB_DOCNAME']]



    def process_item(self, item, spider):
        person_info = dict(item)
        self.post.insert(person_info)
        return item

例程：
test.py

# -*- coding: utf-8 -*-
import scrapy
from test_scrapy.items import TestScrapyItem


class TestSpider(scrapy.Spider):
    name = 'test'
    allowed_domains = ['exercise.kingname.info']
    start_urls = ['http://exercise.kingname.info/exercise_xpath_3.html']

    def parse(self, response):
        person_list = response.xpath('//div[@class="person_table"]/table/tbody/tr')
        for person in person_list:
            item = TestScrapyItem()
            person_info = person.xpath('td/text()').extract()
            item['name'] = person_info[0]
            item['age'] = person_info[1]
            item['salary'] = person_info[2]
            item['phone'] = person_info[3]
            print(person_info)
            yield item

items.py

import scrapy


class TestScrapyItem(scrapy.Item):
        name = scrapy.Field()
        age = scrapy.Field()
        salary = scrapy.Field()
        phone = scrapy.Field()

main.py

from scrapy import cmdline
cmdline.execute("scrapy crawl test".split())

pipelines.py

import pymongo
from scrapy.utils.project import get_project_settings
settings = get_project_settings()

class TestScrapyPipeline:
    def __init__(self):
        host = settings['MONGODB_HOST']
        port = settings['MONGODB_PORT']
        db_name = settings['MONGODB_DBNAME']
        client = pymongo.MongoClient(host=host, port=port)
        db = client[db_name]
        self.post = db[settings['MONGODB_DOCNAME']]

    def process_item(self, item, spider):
        person_info = dict(item)
        self.post.insert(person_info)
        return item

setting.py

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

# Scrapy settings for test_scrapy 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 = 'test_scrapy'

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


# Crawl responsibly by identifying yourself (and your website) on the user-agent
#USER_AGENT = 'test_scrapy (+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,image/webp,image/apng,*/*;q=0.8',
   'accept-encoding': 'gzip, deflate, br',
   'accept-language': 'zh-CN,zh;q=0.9,en;q=0.8',
   'cache-control': 'max-age=0',
   'dnt': '1',
   'upgrade-insecure-requests': '1',
   'user-agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_13_5) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.99 Safari/537.36'
}

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

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


MONGODB_HOST = '127.0.0.1'
MONGODB_PORT = 27017
MONGODB_DBNAME = 'blogspider'
MONGODB_DOCNAME = 'blog'

引入请求头

在setting.py中：

DEFAULT_REQUEST_HEADERS = {}

                     欢迎关注