创建一个新项目comment:
scrapy startproject comment
items.py
import scrapy class CommentItem(scrapy.Item): comments = scrapy.Field()
spider.py
from scrapy import Request,Spider from lxml import etree from comment.items import CommentItem #你想爬取哪一部电影,将其余的两部注释即可。 class CommentSpider(Spider): \'\'\' 这个是三生三世十里桃花 \'\'\' name = \'comment\' def start_requests(self): templateurl = \'https://movie.douban.com/subject/25823277/comments?start={}&limit=20&sort=new_score&status=P\' for i in range(3201): url = templateurl.format(str(i * 20)) yield Request(url=url, callback=self.parse) def parse(self, response): selector = etree.HTML(response.text) item = SanshengItem() item[\'comments\'] = selector.xpath(\'//div[@class="comment"]/p/text()\') yield item # class CommentSpider(Spider): # \'\'\' # 这个是二十二 # \'\'\' # name = \'comment\' # # def start_requests(self): # templateurl = \'https://movie.douban.com/subject/26430107/comments?start={}&limit=20&sort=new_score&status=P\' # for i in range(1601): # url = templateurl.format(str(i * 20)) # yield Request(url=url, callback=self.parse) # # def parse(self, response): # selector = etree.HTML(response.text) # item = SanshengItem() # item[\'comments\'] = selector.xpath(\'//div[@class="comment"]/p/text()\') # yield item # # class CommentSpider(Spider): # \'\'\' # 这个是战狼 # \'\'\' # name = \'comment\' # # def start_requests(self): # templateurl = \'https://movie.douban.com/subject/26363254/comments?start={}&limit=20&sort=new_score&status=P\' # for i in range(9001): # url = templateurl.format(str(i * 20)) # yield Request(url=url, callback=self.parse) # # def parse(self, response): # selector = etree.HTML(response.text) # item = SanshengItem() # item[\'comments\'] = selector.xpath(\'//div[@class="comment"]/p/text()\') # yield item
pipelines.py
import pymongo class MongoPipeline(object): collection = \'sansheng\' # 三生的数据表 # collection = \'ershier\' # 二十二的数据表 # collection = \'zhanlang\' # 战狼的数据表 def __init__(self, mongo_uri, mongo_db): self.mongo_uri = mongo_uri self.mongo_db = mongo_db @classmethod def from_crawler(cls, crawler): return cls( mongo_uri = crawler.settings.get(\'MONGO_RUI\'), mongo_db = crawler.settings.get(\'MONGO_DB\') ) def open_spider(self, spider): self.client = pymongo.MongoClient(self.mongo_uri) self.db = self.client[self.mongo_db] def close_spider(self, spider): self.client.close() def process_item(self, item, spider): table = self.db[self.collection] for com in item[\'comments\']: data = dict() data[\'comment\'] = com.strip().replace("\n", "") table.insert_one(data) return item
middlewares.py
import scrapy from scrapy.downloadermiddlewares.useragent import UserAgentMiddleware import random class MyUseragentMiddleware(UserAgentMiddleware): \'\'\' 设置User-Agent \'\'\' def __init__(self, user_agent): self.user_agent = user_agent @classmethod def from_crawler(cls, crawler): return cls( user_agent=crawler.settings.get(\'USER_AGENTS\') ) def process_request(self, request, spider): agent = random.choice(self.user_agent) request.headers[\'User-Agent\'] = agent
settings.py
BOT_NAME = \'comment\' SPIDER_MODULES = [\'comment.spiders\'] NEWSPIDER_MODULE = \'comment.spiders\' ROBOTSTXT_OBEY = False DOWNLOAD_DELAY = 2 COOKIES_ENABLED = False DEFAULT_REQUEST_HEADERS = { \'Accept\': \'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8\', \'Accept-Language\': \'-CN,zh;q=0.8,en-US;q=0.5,en;q=0.3\', \'Cookie\':\'浏览器复制粘贴你的cookie\' } DOWNLOADER_MIDDLEWARES = { \'comment.middlewares.MyUseragentMiddleware\': 400, } USER_AGENTS = [ "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; AcooBrowser; .NET CLR 1.1.4322; .NET CLR 2.0.50727)", "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.0; Acoo Browser; SLCC1; .NET CLR 2.0.50727; Media Center PC 5.0; .NET CLR 3.0.04506)", "Mozilla/4.0 (compatible; MSIE 7.0; AOL 9.5; AOLBuild 4337.35; Windows NT 5.1; .NET CLR 1.1.4322; .NET CLR 2.0.50727)", "Mozilla/5.0 (Windows; U; MSIE 9.0; Windows NT 9.0; en-US)", "Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Win64; x64; Trident/5.0; .NET CLR 3.5.30729; .NET CLR 3.0.30729; .NET CLR 2.0.50727; Media Center PC 6.0)", "Mozilla/5.0 (compatible; MSIE 8.0; Windows NT 6.0; Trident/4.0; WOW64; Trident/4.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; .NET CLR 1.0.3705; .NET CLR 1.1.4322)", "Mozilla/4.0 (compatible; MSIE 7.0b; Windows NT 5.2; .NET CLR 1.1.4322; .NET CLR 2.0.50727; InfoPath.2; .NET CLR 3.0.04506.30)", "Mozilla/5.0 (Windows; U; Windows NT 5.1; zh-CN) AppleWebKit/523.15 (KHTML, like Gecko, Safari/419.3) Arora/0.3 (Change: 287 c9dfb30)", "Mozilla/5.0 (X11; U; Linux; en-US) AppleWebKit/527+ (KHTML, like Gecko, Safari/419.3) Arora/0.6", "Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.8.1.2pre) Gecko/20070215 K-Ninja/2.1.1", "Mozilla/5.0 (Windows; U; Windows NT 5.1; zh-CN; rv:1.9) Gecko/20080705 Firefox/3.0 Kapiko/3.0", "Mozilla/5.0 (X11; Linux i686; U;) Gecko/20070322 Kazehakase/0.4.5", "Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.9.0.8) Gecko Fedora/1.9.0.8-1.fc10 Kazehakase/0.5.6", "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.56 Safari/535.11", "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_3) AppleWebKit/535.20 (KHTML, like Gecko) Chrome/19.0.1036.7 Safari/535.20", "Opera/9.80 (Macintosh; Intel Mac OS X 10.6.8; U; fr) Presto/2.9.168 Version/11.52", "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.11 (KHTML, like Gecko) Chrome/20.0.1132.11 TaoBrowser/2.0 Safari/536.11", "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/21.0.1180.71 Safari/537.1 LBBROWSER", "Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; WOW64; Trident/5.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; .NET4.0C; .NET4.0E; LBBROWSER)", "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; QQDownload 732; .NET4.0C; .NET4.0E; LBBROWSER)", "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.84 Safari/535.11 LBBROWSER", "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.1; WOW64; Trident/5.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; .NET4.0C; .NET4.0E)", "Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; WOW64; Trident/5.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; .NET4.0C; .NET4.0E; QQBrowser/7.0.3698.400)", "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; QQDownload 732; .NET4.0C; .NET4.0E)", "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Trident/4.0; SV1; QQDownload 732; .NET4.0C; .NET4.0E; 360SE)", "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; QQDownload 732; .NET4.0C; .NET4.0E)", "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.1; WOW64; Trident/5.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; .NET4.0C; .NET4.0E)", "Mozilla/5.0 (Windows NT 5.1) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/21.0.1180.89 Safari/537.1", "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/21.0.1180.89 Safari/537.1", "Mozilla/5.0 (iPad; U; CPU OS 4_2_1 like Mac OS X; zh-cn) AppleWebKit/533.17.9 (KHTML, like Gecko) Version/5.0.2 Mobile/8C148 Safari/6533.18.5", "Mozilla/5.0 (Windows NT 6.1; Win64; x64; rv:2.0b13pre) Gecko/20110307 Firefox/4.0b13pre", "Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:16.0) Gecko/20100101 Firefox/16.0", "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.11 (KHTML, like Gecko) Chrome/23.0.1271.64 Safari/537.11", "Mozilla/5.0 (X11; U; Linux x86_64; zh-CN; rv:1.9.2.10) Gecko/20100922 Ubuntu/10.10 (maverick) Firefox/3.6.10", "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.36", ] ITEM_PIPELINES = { \'comment.pipelines.MongoPipeline\': 300, } MONGO_URI = \'mongodb://localhost:27017\' MONGO_DB = "douban"
注意:
请把COOKIES_ENABLED设置为 False,你可能觉得奇怪,为什么我们使用了cookie却需要把它设置为False,原因在于,我们直接把cookie放在了请求头里面,但是scrapy默认自己拥有一套处理cookie的中间件,当你把它设置为True的时候,两者会产生影响,从而请求失败,你可以自己尝试一下。那如果我执意要把他设置为True呢,难道就不能解决了么?当然是可以的,但是我们今天就不在深入的讨论这个问题,以后可以单独解释。
我们这里抓取评论数据是为了之后的分析所用。
参考:
http://www.cnblogs.com/cnkai/p/7418330.html
https://blog.csdn.net/topleeyap/article/details/78911246