爬虫综合大作业

作业来自于：https://edu.cnblogs.com/campus/gzcc/GZCC-16SE1/homework/3159

爬取网路游戏玩家人数排名

 网络游戏排名情况：

代码：

mport requests
from lxml import etree
session = requests.Session()
for id in range(0,251,25):
    URL = 'http://movie.douban.com/top250/?start=' + str(id)
    req = session.get(URL)
    req.encoding = 'utf8'              
    root=etree.HTML(req.content)                
    items = root.xpath('//ol/li/div[@class="item"]')
    for item in items:
        rank,name,alias,rating_num,quote,url = "","","","","",""
        try:
            url = item.xpath('./div[@class="pic"]/a/@href')[0]
            rank = item.xpath('./div[@class="pic"]/em/text()')[0]
            title = item.xpath('./div[@class="info"]//a/span[@class="title"]/text()')
            name = title[0].encode('gb2312','ignore').decode('gb2312')
            alias = title[1].encode('gb2312','ignore').decode('gb2312') if len(title)==2 else ""
            rating_num = item.xpath('.//div[@class="bd"]//span[@class="rating_num"]/text()')[0]
            quote_tag = item.xpath('.//div[@class="bd"]//span[@class="inq"]')
            if len(quote_tag)  is not 0:
                quote = quote_tag[0].text.encode('gb2312','ignore').decode('gb2312').replace('xa0','')
            print(rank,rating_num,quote)
            print(name.encode('gb2312','ignore').decode('gb2312') ,alias.encode('gb2312','ignore').decode('gb2312') .replace('/',','))
        except:
            print('faild!')
            pass

 

获取每一个网络游戏：

def get_html(web_url):  
     header = {
         "User-Agent":"Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US) AppleWebKit/534.16 (KHTML, like Gecko) Chrome/10.0.648.133 Safari/534.16"}
     html = requests.get(url=web_url, headers=header).text
     Soup = BeautifulSoup(html, "lxml")
     data = Soup.find("ol").find_all("li") 
     return data

倒入数据库

sql = "INSERT INTO test(rank, name, tpye,developers, company, " 
          "state, yeas, number) values(%s,%s,%s,%s,%s,%s,%s,%s)"
    try:
        cur.executemany(sql, movies_info)
        db.commit()
    except Exception as e:
        print("Error:", e)

 

核心代码:

importscrapy

fromscrapy importSpider

fromdoubanTop250.items importDoubantop250Item

classDoubanSpider(scrapy.Spider):

name = 'douban'

allowed_domains = ['douban.com']

start_urls = ['https://movie.douban.com/top250/']

defparse(self, response):

lis = response.css('.info')

forli inlis:

item = Doubantop250Item()



name = li.css('.hd span::text').extract()

title = ''.join(name)

info = li.css('p::text').extract()[1].replace('n', '').strip()

score = li.css('.rating_num::text').extract_first()

people = li.css('.star span::text').extract()[1]

words = li.css('.inq::text').extract_first()



item['title'] = title

item['info'] = info

item[number] = number

item['people'] = people

item['words'] = words

yielditem



next = response.css('.next a::attr(href)').extract_first()

ifnext:

url = response.urljoin(next)

yieldscrapy.Request(url=url, callback=self.parse)

pass

生成的items.py文件，是保存爬取数据的容器，代码修改如下。

importscrapy

classDoubantop250Item(scrapy.Item):


title = scrapy.Field()

info = scrapy.Field()

score = scrapy.Field()

people = scrapy.Field()

words = scrapy.Field()
        db.rollback()

 excel表格