七月在线爬虫班学习笔记（六）——scrapy爬虫整体示例
第六课主要内容：
- 爬豆瓣文本例程 douban
- 图片例程 douban_imgs
1.爬豆瓣文本例程 douban
目录结构
douban
--douban
--spiders
--__init__.py
--bookspider.py
--douban_comment_spider.py
--doumailspider.py
--__init__.py
--items.py
--pipelines.py
--settings.py
--scrapy.cfg
–spiders–init.py
# This package will contain the spiders of your Scrapy project # # Please refer to the documentation for information on how to create and manage # your spiders.
bookspider.py
# -*- coding:utf-8 -*-
'''by sudo rm -rf http://imchenkun.com'''
import scrapy
from douban.items import DoubanBookItem
class BookSpider(scrapy.Spider):
name = 'douban-book'
allowed_domains = ['douban.com']
start_urls = [
'https://book.douban.com/top250'
]
def parse(self, response):
# 请求第一页
yield scrapy.Request(response.url, callback=self.parse_next)
# 请求其它页
for page in response.xpath('//div[@class="paginator"]/a'):
link = page.xpath('@href').extract()[0]
yield scrapy.Request(link, callback=self.parse_next)
def parse_next(self, response):
for item in response.xpath('//tr[@class="item"]'):
book = DoubanBookItem()
book['name'] = item.xpath('td[2]/div[1]/a/@title').extract()[0]
book['content'] = item.xpath('td[2]/p/text()').extract()[0]
book['ratings'] = item.xpath('td[2]/div[2]/span[2]/text()').extract()[0]
yield book
douban_comment_spider.py
# -*- coding:utf-8 -*-
#python2中提示输入为raw_input,python3为input；Python2 print不需要加括号，Python3全加。大家可以根据自己的版本自行优化import scrapy from faker import Factory from douban.items import DoubanMovieCommentItem import urllib.parse f = Factory.create() class MailSpider(scrapy.Spider): name = 'douban-comment' allowed_domains = ['accounts.douban.com', 'douban.com'] start_urls = [ 'https://www.douban.com/' ] headers = { 'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8', 'Accept-Encoding': 'gzip, deflate, br', 'Accept-Language': 'zh-CN,zh;q=0.8,en-US;q=0.5,en;q=0.3', 'Connection': 'keep-alive', 'Host': 'accounts.douban.com', 'User-Agent': f.user_agent() } formdata = { 'form_email': '你的邮箱', 'form_password': '你的密码', # 'captcha-solution': '', # 'captcha-id': '', 'login': '登录', 'redir': 'https://www.douban.com/', 'source': 'None' } def start_requests(self): return [scrapy.Request(url='https://www.douban.com/accounts/login', headers=self.headers, meta={'cookiejar': 1}, callback=self.parse_login)] def parse_login(self, response): # 如果有验证码要人为处理 if 'captcha_image' in response.body: print('Copy the link:') link = response.xpath('//img[@class="captcha_image"]/@src').extract()[0] print(link) captcha_solution = input('captcha-solution:') captcha_id = urllib.parse_qs(urllib.urlparse(link).query, True)['id'] self.formdata['captcha-solution'] = captcha_solution self.formdata['captcha-id'] = captcha_id return [scrapy.FormRequest.from_response(response, formdata=self.formdata, headers=self.headers, meta={'cookiejar': response.meta['cookiejar']}, callback=self.after_login )] def after_login(self, response): print (response.status) self.headers['Host'] = "www.douban.com" yield scrapy.Request(url='https://movie.douban.com/subject/22266320/reviews', meta={'cookiejar': response.meta['cookiejar']}, headers=self.headers, callback=self.parse_comment_url) yield scrapy.Request(url='https://movie.douban.com/subject/22266320/reviews', meta={'cookiejar': response.meta['cookiejar']}, headers=self.headers, callback=self.parse_next_page, dont_filter = True) #不去重 def parse_next_page(self, response): print (response.status) try: next_url = response.urljoin(response.xpath('//span[@class="next"]/a/@href').extract()[0]) print ("下一页") print (next_url) yield scrapy.Request(url=next_url, meta={'cookiejar': response.meta['cookiejar']}, headers=self.headers, callback=self.parse_comment_url, dont_filter = True) yield scrapy.Request(url=next_url, meta={'cookiejar': response.meta['cookiejar']}, headers=self.headers, callback=self.parse_next_page, dont_filter = True) except: print ("Next page Error") return def parse_comment_url(self, response): print (response.status) for item in response.xpath('//div[@class="main review-item"]'): comment_url = item.xpath('header/h3[@class="title"]/a/@href').extract()[0] comment_title = item.xpath('header/h3[@class="title"]/a/text()').extract()[0] print (comment_title) print (comment_url) yield scrapy.Request(url=comment_url, meta={'cookiejar': response.meta['cookiejar']}, headers=self.headers, callback=self.parse_comment) def parse_comment(self, response): print (response.status) for item in response.xpath('//div[@id="content"]'): comment = DoubanMovieCommentItem() comment['useful_num'] = item.xpath('//div[@class="main-panel-useful"]/button[1]/text()').extract()[0].strip() comment['no_help_num'] = item.xpath('//div[@class="main-panel-useful"]/button[2]/text()').extract()[0].strip() comment['people'] = item.xpath('//span[@property="v:reviewer"]/text()').extract()[0] comment['people_url'] = item.xpath('//header[@class="main-hd"]/a[1]/@href').extract()[0] comment['star'] = item.xpath('//header[@class="main-hd"]/span[1]/@title').extract()[0] data_type = item.xpath('//div[@id="link-report"]/div/@data-original').extract()[0] print ("data_type: "+data_type) if data_type == '0': comment['comment'] = "\t#####\t".join(map(lambda x:x.strip(), item.xpath('//div[@id="link-report"]/div/p/text()').extract())) elif data_type == '1': comment['comment'] = "\t#####\t".join(map(lambda x:x.strip(), item.xpath('//div[@id="link-report"]/div[1]/text()').extract())) comment['title'] = item.xpath('//span[@property="v:summary"]/text()').extract()[0] comment['comment_page_url'] = response.url #print comment yield comment
doumailspider.py
# -*- coding:utf-8 -*-
'''by sudo rm -rf http://imchenkun.com'''
import scrapy
from faker import Factory
from douban.items import DoubanMailItem
import urllib.parse
f = Factory.create()
class MailSpider(scrapy.Spider):
name = 'douban-mail'
allowed_domains = ['accounts.douban.com', 'douban.com']
start_urls = [
'https://www.douban.com/'
]
headers = {
'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
'Accept-Encoding': 'gzip, deflate, br',
'Accept-Language': 'zh-CN,zh;q=0.8,en-US;q=0.5,en;q=0.3',
'Connection': 'keep-alive',
'Host': 'accounts.douban.com',
'User-Agent': f.user_agent()
}
formdata = {
'form_email': '你的邮箱',
'form_password': '你的密码',
# 'captcha-solution': '',
# 'captcha-id': '',
'login': '登录',
'redir': 'https://www.douban.com/',
'source': 'None'
}
def start_requests(self):
return [scrapy.Request(url='https://www.douban.com/accounts/login',
headers=self.headers,
meta={'cookiejar': 1},
callback=self.parse_login)]
def parse_login(self, response):
# 如果有验证码要人为处理
if 'captcha_image' in response.body:
print ('Copy the link:')
link = response.xpath('//img[@class="captcha_image"]/@src').extract()[0]
print (link)
captcha_solution = input('captcha-solution:')
captcha_id = urllib.parse_qs(urllib.urlparse(link).query, True)['id']
self.formdata['captcha-solution'] = captcha_solution
self.formdata['captcha-id'] = captcha_id
return [scrapy.FormRequest.from_response(response,
formdata=self.formdata,
headers=self.headers,
meta={'cookiejar': response.meta['cookiejar']},
callback=self.after_login
)]
def after_login(self, response):
print (response.status)
self.headers['Host'] = "www.douban.com"
return scrapy.Request(url='https://www.douban.com/doumail/',
meta={'cookiejar': response.meta['cookiejar']},
headers=self.headers,
callback=self.parse_mail)
def parse_mail(self, response):
print (response.status)
for item in response.xpath('//div[@class="doumail-list"]/ul/li'):
mail = DoubanMailItem()
mail['sender_time'] = item.xpath('div[2]/div/span[1]/text()').extract()[0]
mail['sender_from'] = item.xpath('div[2]/div/span[2]/text()').extract()[0]
mail['url'] = item.xpath('div[2]/p/a/@href').extract()[0]
mail['title'] = item.xpath('div[2]/p/a/text()').extract()[0]
print (mail)
yield mail
init.py
无代码
items.py
# -*- coding: utf-8 -*-
import scrapy
class DoubanBookItem(scrapy.Item):
name = scrapy.Field() # 书名
price = scrapy.Field() # 价格
edition_year = scrapy.Field() # 出版年份
publisher = scrapy.Field() # 出版社
ratings = scrapy.Field() # 评分
author = scrapy.Field() # 作者
content = scrapy.Field()
class DoubanMailItem(scrapy.Item):
sender_time = scrapy.Field() # 发送时间
sender_from = scrapy.Field() # 发送人
url = scrapy.Field() # 豆邮详细地址
title = scrapy.Field() # 豆邮标题
class DoubanMovieCommentItem(scrapy.Item):
useful_num = scrapy.Field() # 多少人评论有用
no_help_num = scrapy.Field() # 多少人评论无用
people = scrapy.Field() # 评论者
people_url = scrapy.Field() # 评论者页面
star = scrapy.Field() # 评分
comment = scrapy.Field() # 评论
title = scrapy.Field() # 标题
comment_page_url = scrapy.Field()# 当前页
pipelines.py
# -*- coding: utf-8 -*-
class DoubanBookPipeline(object):
def process_item(self, item, spider):
info = item['content'].split(' / ') # [法] 圣埃克苏佩里 / 马振聘 / 人民文学出版社 / 2003-8 / 22.00元
item['name'] = item['name']
item['price'] = info[-1]
item['edition_year'] = info[-2]
item['publisher'] = info[-3]
return item
class DoubanMailPipeline(object):
def process_item(self, item, spider):
item['title'] = item['title'].replace(' ', '').replace('\\n', '')
return item
class DoubanMovieCommentPipeline(object):
def process_item(self, item, spider):
return item
settings.py
# -*- coding: utf-8 -*-
# Scrapy settings for douban project
#
# For simplicity, this file contains only settings considered important or
# commonly used. You can find more settings consulting the documentation:
#
# http://doc.scrapy.org/en/latest/topics/settings.html
# http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
# http://scrapy.readthedocs.org/en/latest/topics/spider-middleware.html
BOT_NAME = 'douban'
SPIDER_MODULES = ['douban.spiders']
NEWSPIDER_MODULE = 'douban.spiders'
# Crawl responsibly by identifying yourself (and your website) on the user-agent
from faker import Factory
f = Factory.create()
USER_AGENT = f.user_agent()
# Obey robots.txt rules
ROBOTSTXT_OBEY = True
# Configure maximum concurrent requests performed by Scrapy (default: 16)
#CONCURRENT_REQUESTS = 32
# Configure a delay for requests for the same website (default: 0)
# See http://scrapy.readthedocs.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 = {
'Host': 'book.douban.com',
'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
'Accept-Language': 'zh-CN,zh;q=0.8,en-US;q=0.5,en;q=0.3',
'Accept-Encoding': 'gzip, deflate, br',
'Connection': 'keep-alive',
}
#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 http://scrapy.readthedocs.org/en/latest/topics/spider-middleware.html
#SPIDER_MIDDLEWARES = {
# 'douban.middlewares.MyCustomSpiderMiddleware': 543,
#}
# Enable or disable downloader middlewares
# See http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
#DOWNLOADER_MIDDLEWARES = {
# 'douban.middlewares.MyCustomDownloaderMiddleware': 543,
#}
# Enable or disable extensions
# See http://scrapy.readthedocs.org/en/latest/topics/extensions.html
#EXTENSIONS = {
# 'scrapy.extensions.telnet.TelnetConsole': None,
#}
# Configure item pipelines
# See http://scrapy.readthedocs.org/en/latest/topics/item-pipeline.html
ITEM_PIPELINES = {
#'douban.pipelines.DoubanBookPipeline': 300,
#'douban.pipelines.DoubanMailPipeline': 600,
'douban.pipelines.DoubanMovieCommentPipeline': 900,
}
# Enable and configure the AutoThrottle extension (disabled by default)
# See http://doc.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 http://scrapy.readthedocs.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'
scrapy.cfg
# Automatically created by: scrapy startproject # # For more information about the [deploy] section see: # https://scrapyd.readthedocs.org/en/latest/deploy.html [settings] default = douban.settings [deploy] #url = http://localhost:6800/ project = douban
2.图片例程 douban_imgs
目录结构
douban_imgs
--douban
--spiders
--__init__.py
--download_douban.py
--__init__.py
--items.py
--pipelines.py
--run_spider.py
--settings.py
--scrapy.cfg
–spiders–init.py
# This package will contain the spiders of your Scrapy project # # Please refer to the documentation for information on how to create and manage # your spiders.
download_douban.py
# coding=utf-8
from scrapy.spiders import Spider
import re
from scrapy import Request
from douban_imgs.items import DoubanImgsItem
class download_douban(Spider):
name = 'download_douban'
default_headers = {
'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8',
'Accept-Encoding': 'gzip, deflate, sdch, br',
'Accept-Language': 'zh-CN,zh;q=0.8,en;q=0.6',
'Cache-Control': 'max-age=0',
'Connection': 'keep-alive',
'Host': 'www.douban.com',
'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_11_4) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/52.0.2743.116 Safari/537.36',
}
def __init__(self, url='1638835355', *args, **kwargs):
self.allowed_domains = ['douban.com']
self.start_urls = [
'http://www.douban.com/photos/album/%s/' % (url)]
self.url = url
# call the father base function
#super(download_douban, self).__init__(*args, **kwargs)
def start_requests(self):
for url in self.start_urls:
yield Request(url=url, headers=self.default_headers, callback=self.parse)
def parse(self, response):
list_imgs = response.xpath('//div[@class="photolst clearfix"]//img/@src').extract()
if list_imgs:
item = DoubanImgsItem()
item['image_urls'] = list_imgs
yield item
init.py
此文件内无代码
items.py
# -*- coding: utf-8 -*-
# Define here the models for your scraped items
#
# See documentation in:
# http://doc.scrapy.org/en/latest/topics/items.html
import scrapy
from scrapy import Item, Field
class DoubanImgsItem(scrapy.Item):
# define the fields for your item here like:
# name = scrapy.Field()
image_urls = Field()
images = Field()
image_paths = Field()
pipelines.py
# -*- coding: utf-8 -*-
# Define your item pipelines here
#
# Don't forget to add your pipeline to the ITEM_PIPELINES setting
# See: http://doc.scrapy.org/en/latest/topics/item-pipeline.html
from scrapy.pipelines.images import ImagesPipeline
from scrapy.exceptions import DropItem
from scrapy import Request
from scrapy import log
class DoubanImgsPipeline(object):
def process_item(self, item, spider):
return item
class DoubanImgDownloadPipeline(ImagesPipeline):
default_headers = {
'accept': 'image/webp,image/*,*/*;q=0.8',
'accept-encoding': 'gzip, deflate, sdch, br',
'accept-language': 'zh-CN,zh;q=0.8,en;q=0.6',
'cookie': 'bid=yQdC/AzTaCw',
'referer': 'https://www.douban.com/photos/photo/2370443040/',
'user-agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_11_4) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/52.0.2743.116 Safari/537.36',
}
def get_media_requests(self, item, info):
for image_url in item['image_urls']:
self.default_headers['referer'] = image_url
yield Request(image_url, headers=self.default_headers)
def item_completed(self, results, item, info):
image_paths = [x['path'] for ok, x in results if ok]
if not image_paths:
raise DropItem("Item contains no images")
item['image_paths'] = image_paths
return item
run_spider.py
from scrapy import cmdline
cmd_str = 'scrapy crawl download_douban'
cmdline.execute(cmd_str.split(' '))
settings.py
# -*- coding: utf-8 -*-
# Scrapy settings for douban_imgs project
#
# For simplicity, this file contains only settings considered important or
# commonly used. You can find more settings consulting the documentation:
#
# http://doc.scrapy.org/en/latest/topics/settings.html
# http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
# http://scrapy.readthedocs.org/en/latest/topics/spider-middleware.html
BOT_NAME = 'douban_imgs'
SPIDER_MODULES = ['douban_imgs.spiders']
NEWSPIDER_MODULE = 'douban_imgs.spiders'
# Crawl responsibly by identifying yourself (and your website) on the user-agent
# USER_AGENT = 'douban_imgs (+http://www.yourdomain.com)'
# Configure maximum concurrent requests performed by Scrapy (default: 16)
# CONCURRENT_REQUESTS=32
# Configure a delay for requests for the same website (default: 0)
# See http://scrapy.readthedocs.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 http://scrapy.readthedocs.org/en/latest/topics/spider-middleware.html
# SPIDER_MIDDLEWARES = {
# 'douban_imgs.middlewares.MyCustomSpiderMiddleware': 543,
# }
# Enable or disable downloader middlewares
# See http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
# DOWNLOADER_MIDDLEWARES = {
# 'douban_imgs.middlewares.MyCustomDownloaderMiddleware': 543,
# }
# Enable or disable extensions
# See http://scrapy.readthedocs.org/en/latest/topics/extensions.html
# EXTENSIONS = {
# 'scrapy.telnet.TelnetConsole': None,
# }
# Configure item pipelines
# See http://scrapy.readthedocs.org/en/latest/topics/item-pipeline.html
ITEM_PIPELINES = {
'douban_imgs.pipelines.DoubanImgDownloadPipeline': 300,
}
IMAGES_STORE = 'D:\\doubanimgs'
#IMAGES_STORE = '/tmp'
IMAGES_EXPIRES = 90
# Enable and configure the AutoThrottle extension (disabled by default)
# See http://doc.scrapy.org/en/latest/topics/autothrottle.html
# NOTE: AutoThrottle will honour the standard settings for concurrency and delay
# 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
# Enable showing throttling stats for every response received:
# AUTOTHROTTLE_DEBUG=False
# Enable and configure HTTP caching (disabled by default)
# See http://scrapy.readthedocs.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'
scrapy.cfg
# Automatically created by: scrapy startproject # # For more information about the [deploy] section see: # https://scrapyd.readthedocs.org/en/latest/deploy.html [settings] default = douban_imgs.settings [deploy] #url = http://localhost:6800/ project = douban_imgs
情不知所起一往而深
