2019-08-01

如何下载图片

# 图片的下载
import requests
url = '[http://g.hiphotos.baidu.com/image/pic/item/5366d0160924ab18014cefd83bfae6cd7a890b82.jpg](qq://txfile/#)'
response = requests.get(url)
# 获取bytes类型的响应
data = response.content
with open('风景.jpg','wb') as f:
    f.write(data)

如何翻页

观察网页翻页后url的变化，运用range和参数传递实现翻页。

  for i in range(0, 250, 25):
        url = 'https://movie.douban.com/top250?start={}&filter='.format(i)

25为每一页展示的电影数量；start=x表示当前页面从序号x的电影开始。

1. 豆瓣电影TOP250爬虫

• html源码

  
  
  豆瓣TOP250源码

• 代码实现

import requests
from lxml import etree
def spider_douban_top250():
    movie_list_info = []
    headers = {"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.142 Safari/537.36"}
    
    #观察网页翻页url的变化，运用range和参数传递实现翻页
    for i in range(0, 250, 25):
        url = 'https://movie.douban.com/top250?start={}&filter='.format(i)

        # 获取bytes类型响应
        data = requests.get(url, headers=headers).content
        html = etree.HTML(data)



        ol_list = html.xpath('//div[@id="content"]//div[@class="article"]/ol/li')

        for movie in ol_list:
            # 影片序号
            serial_number = movie.xpath('./div[@class="item"]/div[@class="pic"]/em/text()')
            if len(serial_number) == 0:
                serial_number = ''
            else:
                serial_number = serial_number[0]
            # print(serial_number)
            # 电影的名字
            movie_name = movie.xpath('./div[@class="item"]/div[@class="info"]/div[@class="hd"]/a/span[1]/text()')[0]
            # print(movie_name)
            # 电影的介绍
            movie_introduce = movie.xpath('./div[@class="item"]/div[@class="info"]/div[@class="bd"]/p[1]/text()')[
                0].strip()
            # print(movie_introduce)
            # 电影的星级
            star = \
            movie.xpath('./div[@class="item"]/div[@class="info"]/div[@class="bd"]/div[@class="star"]/span[2]/text()')[0]
            # print(star)
            # 电影的评价
            evalute = movie.xpath(
                './div[@class="item"]/div[@class="info"]/div[@class="bd"]/div[@class="star"]/span[4]/text()')
            evalute = evalute[0].replace('人评价', '')
            # print(evalute)
            # 电影的描述
            describe = movie.xpath('./div[@class="item"]/div[@class="info"]/div[@class="bd"]/p[@class="quote"]/span[1]/text()')
            # print(describe)
            # 电影封面的地址
            movie_img_url = movie.xpath('./div[@class="item"]/div[@class="pic"]/a/img/@src')[0]
            # print(movie_img_url)

            movie_list_info.append({
                'serial_number': serial_number,
                'movie_name': movie_name,
                'movie_introduce': movie_introduce,
                'star': star,
                'evalute': evalute,
                'describe': describe,
                'movie_img_url': movie_img_url
            })
    for movie in movie_list_info:
        print(movie)

        # 下载图片
    for movie in movie_list_info:
        url = movie['movie_img_url']
        resp = requests.get(url)
        if resp.status_code == 200:
            img_name = '0000000{}.jpg'.format(movie['serial_number'])
            with open('./imgs/{}'.format(img_name), 'wb') as f:
                f.write(resp.content)


spider_douban_top250()

这里使用的是lxml.etree而不是之前的lxml.html，得到结果基本一致，但etree功能更多。

• 爬取结果

  
  
  爬取的电影信息
  
  
  下载的图片

2. 爬取7k7k游戏信息

• 7k7k网页源码

  
  
  7k7k源码
• 代码实现

import requests
from lxml import etree
def spider_7k7k_top100():
    game_list_info = []
    headers = {"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.142 Safari/537.36"}
    #爬取10页
    for i in range(0, 10):
        url = 'http://www.7k7k.com/tag/134/index_{}.htm#p-anchor'.format(i)

        # 获取bytes类型响应
        data = requests.get(url, headers=headers).content
        html = etree.HTML(data)



        ul_list = html.xpath('//div[@id="recommend-new-most"]//div[@class="ui-slide-cont"]/ul/li')
        #print(ul_list)

        for game in ul_list:
            # 游戏名字
            game_name = game.xpath('./a[@class="li-top-a"]/span/text()')
            print(game_name)

            # 游戏封面的地址
            imgs =  game.xpath('./a[@class="li-top-a"]/img/@src')
            if imgs:
                game_img_url = game.xpath('./a[@class="li-top-a"]/img/@src')[0]
            print(game_img_url)


            # 游戏链接
            game_link = 'http://www.7k7k.com{}'.format(game.xpath('./a[@class="li-top-a"]/@href')[0])
            #game_link = game.xpath('./a[@class="li-top-a"]/@href')[0]
            print(game_link)


            game_list_info.append({
                'game_name': game_name,
                'game_link': game_link,
                'game_img_url': game_img_url
            })
    for game in game_list_info:
        print(game)

    #下载图片
    index = 1; #图片索引
    for game in game_list_info:
        url = game['game_img_url']
        resp = requests.get(url)
        if resp.status_code == 200:
            img_name = '0000000{}.jpg'.format(i)
            with open('./imgs/{}'.format(img_name), 'wb') as f:
                f.write(resp.content)
        i += 1


spider_7k7k_top100()

• 爬取结果

  
  
  爬取结果

• 游戏封面

  
  
  下载游戏封面