item段
import scrapy
class DoubanItem(scrapy.Item):
book_name = scrapy.Field()
ID_name = scrapy.Field()
comment = scrapy.Field()
# define the fields for your item here like:
# name = scrapy.Field()
pass
spider段
import scrapy,bs4
from ..items import DoubanItem
class DoubantopSpider(scrapy.Spider):
name = 'doubantop'
allowed_domains = ['book.douban.com']
start_urls = []
for x in range(2):
url = 'https://book.douban.com/top250?start=' + str(x * 25)
start_urls.append(url)
def parse(self, response):
soup = bs4.BeautifulSoup(response.text,'html.parser')
datas = soup.find_all('tr',class_='item')
for data in datas:
book_url = data.find_all('a')[1]['href']
comment_url = book_url+'comments/'
yield scrapy.Request(comment_url,callback=self.parse_comment)
def parse_comment(self,response):
soup = bs4.BeautifulSoup(response.text,'html.parser')
book_name = soup.find('div',id='content').text.split()[0]
datas = soup.find_all('div',class_='comment')
for data in datas:
item = DoubanItem()
item['book_name'] = book_name
item['ID_name'] = data.find_all('a')[1].text
item['comment'] = data.find('span',class_='short').text
yield item
settings段
BOT_NAME = 'douban'
SPIDER_MODULES = ['douban.spiders']
NEWSPIDER_MODULE = 'douban.spiders'
USER_AGENT = 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/71.0.3578.98 Safari/537.36'
ROBOTSTXT_OBEY = False
ITEM_PIPELINES = {
'douban.pipelines.DoubanPipeline': 300,
}
pipelines段
from itemadapter import ItemAdapter
import openpyxl
class DoubanPipeline:
def __init__(self):
self.wb = openpyxl.Workbook()
self.ws = self.wb.active
self.ws.append(['书名','ID名', '短评'])
def process_item(self, item, spider):
line = [item['book_name'],item['ID_name'], item['comment']]
self.ws.append(line)
return item
def close_spider(self,spider):
self.wb.save('book.xlsx')
self.wb.close()
main段
from scrapy import cmdline
cmdline.execute(['scrapy','crawl','doubantop'])
终端
E:\python\douban>c:/users/moneydragon/appdata/local/programs/python/python39/python.exe e:/python/douban/main.py
2021-06-22 17:16:47 [scrapy.utils.log] INFO: Scrapy 2.5.0 started (bot: douban)
2021-06-22 17:16:47 [scrapy.utils.log] INFO: Versions: lxml 4.6.3.0, libxml2 2.9.5, cssselect 1.1.0, parsel 1.6.0, w3lib 1.22.0, Twisted 21.2.0, Python 3.9.0 (tags/v3.9.0:9cf6752, Oct 5 2020, 15:34:40) [MSC v.1927 64 bit (AMD64)], pyOpenSSL 20.0.1 (OpenSSL 1.1.1k 25 Mar 2021), cryptography 3.4.7, Platform Windows-10-10.0.19041-SP0
2021-06-22 17:16:47 [scrapy.utils.log] DEBUG: Using reactor: twisted.internet.selectreactor.SelectReactor
2021-06-22 17:16:47 [scrapy.crawler] INFO: Overridden settings:
{'BOT_NAME': 'douban',
'NEWSPIDER_MODULE': 'douban.spiders',
'SPIDER_MODULES': ['douban.spiders'],
'USER_AGENT': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 '
'(KHTML, like Gecko) Chrome/71.0.3578.98 Safari/537.36'}
2021-06-22 17:16:47 [scrapy.extensions.telnet] INFO: Telnet Password: 0a00dfae751dd926
2021-06-22 17:16:47 [scrapy.middleware] INFO: Enabled extensions:
['scrapy.extensions.corestats.CoreStats',
'scrapy.extensions.telnet.TelnetConsole',
'scrapy.extensions.logstats.LogStats']
2021-06-22 17:16:48 [scrapy.middleware] INFO: Enabled downloader middlewares:
['scrapy.downloadermiddlewares.httpauth.HttpAuthMiddleware',
'scrapy.downloadermiddlewares.downloadtimeout.DownloadTimeoutMiddleware',
'scrapy.downloadermiddlewares.defaultheaders.DefaultHeadersMiddleware',
'scrapy.downloadermiddlewares.useragent.UserAgentMiddleware',
'scrapy.downloadermiddlewares.retry.RetryMiddleware',
'scrapy.downloadermiddlewares.redirect.MetaRefreshMiddleware',
'scrapy.downloadermiddlewares.httpcompression.HttpCompressionMiddleware',
'scrapy.downloadermiddlewares.redirect.RedirectMiddleware',
'scrapy.downloadermiddlewares.cookies.CookiesMiddleware',
'scrapy.downloadermiddlewares.httpproxy.HttpProxyMiddleware',
'scrapy.downloadermiddlewares.stats.DownloaderStats']
2021-06-22 17:16:48 [scrapy.middleware] INFO: Enabled spider middlewares:
['scrapy.spidermiddlewares.httperror.HttpErrorMiddleware',
'scrapy.spidermiddlewares.offsite.OffsiteMiddleware',
'scrapy.spidermiddlewares.referer.RefererMiddleware',
'scrapy.spidermiddlewares.urllength.UrlLengthMiddleware',
'scrapy.spidermiddlewares.depth.DepthMiddleware']
2021-06-22 17:16:48 [scrapy.middleware] INFO: Enabled item pipelines:
['douban.pipelines.DoubanPipeline']
2021-06-22 17:16:48 [scrapy.core.engine] INFO: Spider opened
2021-06-22 17:16:48 [scrapy.extensions.logstats] INFO: Crawled 0 pages (at 0 pages/min), scraped 0 items (at 0 items/min)
2021-06-22 17:16:48 [scrapy.extensions.telnet] INFO: Telnet console listening on 127.0.0.1:6023
2021-06-22 17:16:48 [scrapy.core.engine] DEBUG: Crawled (200) <GET https://book.douban.com/top250?start=25> (referer: None)
2021-06-22 17:16:48 [scrapy.core.engine] DEBUG: Crawled (200) <GET https://book.douban.com/top250?start=0> (referer: None)
2021-06-22 17:16:48 [scrapy.core.engine] INFO: Closing spider (finished)
2021-06-22 17:16:48 [scrapy.statscollectors] INFO: Dumping Scrapy stats:
{'downloader/request_bytes': 609,
'downloader/request_count': 2,
'downloader/request_method_count/GET': 2,
'downloader/response_bytes': 1131,
'downloader/response_count': 2,
'downloader/response_status_count/200': 2,
'elapsed_time_seconds': 0.387873,
'finish_reason': 'finished',
'finish_time': datetime.datetime(2021, 6, 22, 9, 16, 48, 769793),
'httpcompression/response_bytes': 517,
'httpcompression/response_count': 2,
'log_count/DEBUG': 2,
'log_count/INFO': 10,
'response_received_count': 2,
'scheduler/dequeued': 2,
'scheduler/dequeued/memory': 2,
'scheduler/enqueued': 2,
'scheduler/enqueued/memory': 2,
'start_time': datetime.datetime(2021, 6, 22, 9, 16, 48, 381920)}
2021-06-22 17:16:48 [scrapy.core.engine] INFO: Spider closed (finished)
