Python Scrapy 实战
Python Scrapy
什么是爬虫?
网络爬虫(英语:web crawler),也叫网络蜘蛛(spider),是一种用来自动浏览万维网的网络机器人。其目的一般为编纂网络索引。
Python 爬虫
在爬虫领域,Python几乎是霸主地位,将网络一切数据作为资源,通过自动化程序进行有针对性的数据采集以及处理。从事该领域应学习爬虫策略、高性能异步IO、分布式爬虫等,并针对Scrapy框架源码进行深入剖析,从而理解其原理并实现自定义爬虫框架。
Python 爬虫爬虫框架 Scrapy
Scrapy 是用 Python 编写实现的一个为了爬取网站数据、提取结构性数据而编写的应用框架。Scrapy 常应用在包括数据挖掘,信息处理或存储历史数据等一系列的程序中。
Python Scrapy 核心
Scrapy Engine(引擎): 负责Spider、ItemPipeline、Downloader、Scheduler中间的通讯,信号、数据传递等。
**Scheduler(调度器): **它负责接受引擎发送过来的Request请求,并按照一定的方式进行整理排列,入队,当引擎需要时,交还给引擎。
Downloader(下载器):负责下载Scrapy Engine(引擎)发送的所有Requests请求,并将其获取到的Responses交还给Scrapy Engine(引擎),由引擎交给Spider来处理,
Spider(爬虫):它负责处理所有Responses,从中分析提取数据,获取Item字段需要的数据,并将需要跟进的URL提交给引擎,再次进入Scheduler(调度器).
Item Pipeline(管道):它负责处理Spider中获取到的Item,并进行进行后期处理(详细分析、过滤、存储等)的地方。
Downloader Middlewares(下载中间件):你可以当作是一个可以自定义扩展下载功能的组件。
Spider Middlewares(Spider中间件):你可以理解为是一个可以自定扩展和操作引擎和Spider中间通信的功能组件(比如进入Spider的Responses;和从Spider出去的Requests)
Scrapy Demo
# 创建爬虫虚拟环境
$ conda create --name scrapy python=3.6
# 激活虚拟环境
$ activate scrapy
# 安装scrapy
$ conda install scrapy
# 使用 scrapy 提供的工具创建爬虫项目
$ scrapy startproject myScrapy
# 启动爬虫
$ scrapy crawl scrapyName
项目文件介绍
-
scrapy.cfg: 项目的配置文件。
-
mySpider/: 项目的Python模块,将会从这里引用代码。
-
mySpider/items.py: 项目的目标文件。
-
mySpider/pipelines.py: 项目的管道文件。
-
mySpider/settings.py: 项目的设置文件。
-
mySpider/spiders/: 存储爬虫代码目录。
爬取豆瓣 top250
- item.py
import scrapy
class DoubanItem(scrapy.Item):
name = scrapy.Field()
director = scrapy.Field()
detail = scrapy.Field()
star = scrapy.Field()
synopsis = scrapy.Field()
comment = scrapy.Field()
- spiders/DoubanSpider.py
# coding:utf-8
import scrapy
from scrapy import Request
from douban.items import DoubanItem
class DoubanSpider(scrapy.Spider):
name = "douban"
allowed_domains = ['douban.com']
start_urls = ['https://movie.douban.com/top250']
def parse(self, response):
movie_list = response.xpath("//div[@class='article']/ol/li")
if movie_list and len(movie_list) > 0:
for movie in movie_list:
item = DoubanItem()
item['name'] = movie.xpath("./div/div[2]/div[1]/a/span[1]/text()").extract()[0]
item['director'] = movie.xpath("normalize-space(./div/div[2]/div[2]/p/text())").extract_first()
item['detail'] = movie.xpath("normalize-space(./div/div[2]/div[2]/p[1]/text())").extract()[0]
item['star'] = movie.xpath("./div/div[2]/div[2]/div/span[2]/text()").extract()[0]
item['synopsis'] = movie.xpath("normalize-space(./div/div[2]/div[2]/p[2]/span/text())").extract()[0]
item['comment'] = movie.xpath("./div/div[2]/div[2]/div/span[4]/text()").extract()[0]
yield item
next_link = response.xpath("//span[@class='next']/a/@href").extract()
if next_link:
yield Request("https://movie.douban.com/top250" + next_link[0], callback=self.parse, dont_filter=True)
- 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
from database_handler import DatabaseHandler
class DoubanPipeline(object):
def __init__(self):
self.db = DatabaseHandler(host="xxx", username="xxx", password="xxx", database="xxx")
def close_spider(self, spider):
self.db.close()
# 将 Item 实例保存到文件
def process_item(self, item, spider):
sql = "insert into t_douban(name,director,detail,star,synopsis,comment) values('%s', '%s', '%s', '%s', '%s', '%s')" % (
item['name'], item['director'], item['detail'], item['star'], item['synopsis'], item['comment'])
self.db.insert(sql)
return item
- DatabaseHandler.py
# coding:utf-8
import pymysql
from pymysql.err import *
class DatabaseHandler(object):
def __init__(self, host, username, password, database, port=3306):
"""初始化数据库连接"""
self.host = host
self.username = username
self.password = password
self.port = port
self.database = database
self.db = pymysql.connect(self.host, self.username, self.password, self.database, self.port, charset='utf8')
self.cursor = None
def execute(self, sql):
"""执行SQL语句"""
try:
self.cursor = self.db.cursor()
self.cursor.execute(sql)
self.db.commit()
except (MySQLError, ProgrammingError) as e:
print(e)
self.db.rollback()
else:
print("rowCount: %s rowNumber: %s" % (self.cursor.rowcount, self.cursor.rownumber))
finally:
self.cursor.close()
def update(self, sql):
""" 更新操作"""
self.execute(sql)
def insert(self, sql):
"""插入数据"""
self.execute(sql)
return self.cursor.lastrowid
def insert_bath(self, sql, rows):
"""批量插入"""
try:
self.cursor.executemany(sql, rows)
self.db.commit()
except (MySQLError, ProgrammingError) as e:
print(e)
self.db.rollback()
else:
print("rowCount: %s rowNumber: %s" % (self.cursor.rowcount, self.cursor.rownumber))
finally:
self.cursor.close()
def delete(self, sql):
"""删除数据"""
self.execute(sql)
def select(self, sql):
"""查询数据 返回 map 类型的数据"""
self.cursor = self.db.cursor(cursor=pymysql.cursors.DictCursor)
result = []
try:
self.cursor.execute(sql)
data = self.cursor.fetchall()
for row in data:
result.append(row)
except MySQLError as e:
print(e)
else:
print(f"rowCount: {self.cursor.rowcount} rowNumber: {self.cursor.rownumber}")
return result
finally:
self.cursor.close()
def call_proc(self, name):
"""调用存储过程"""
self.cursor.callproc(name)
return self.cursor.fetchone()
def close(self):
"""关闭连接"""
self.db.close()
if __name__ == "__main__":
pass
- 修改settings.py
USER_AGENT = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/76.0.3809.132 Safari/537.36'
ITEM_PIPELINES = {
'mySpider.pipelines.DoubanPipeline': 300,
}
run
scrapy crawl douban