2023-5-16
爬取网站图片1.5版
2023-5-16 18:10
1.1.0版本仅对第一页实现了爬取，2.0版本的目标是实现整个爬取。但是我发现在我开始写2.0版本的时候发现自己的代码，太乱了！！！所以我在进行2.0之前，先进行一下1.5版，封装一下部分代码。
2023-5-16 19:12
2.在封装1.5的时候，写着写着把2.0也实现了emmm，差不多一个小时，实现了全部页面图片的爬取下载，共爬取44张网页，爬取图片爬了1638张。后面再改进改进代码吧，还是有点乱。

import random
from selenium import webdriver
import time
from lxml import etree
import requests

user_agent = [
    "Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_8; en-us) AppleWebKit/534.50 (KHTML, like Gecko) Version/5.1 Safari/534.50",
    "Mozilla/5.0 (Windows; U; Windows NT 6.1; en-us) AppleWebKit/534.50 (KHTML, like Gecko) Version/5.1 Safari/534.50",
    "Mozilla/5.0 (Windows NT 10.0; WOW64; rv:38.0) Gecko/20100101 Firefox/38.0",
    "Mozilla/5.0 (Windows NT 10.0; WOW64; Trident/7.0; .NET4.0C; .NET4.0E; .NET CLR 2.0.50727; .NET CLR 3.0.30729; .NET CLR 3.5.30729; InfoPath.3; rv:11.0) like Gecko",
    "Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Trident/5.0)",
    "Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 6.0; Trident/4.0)",
    "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.0)",
    "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1)",
    "Mozilla/5.0 (Macintosh; Intel Mac OS X 10.6; rv:2.0.1) Gecko/20100101 Firefox/4.0.1",
    "Mozilla/5.0 (Windows NT 6.1; rv:2.0.1) Gecko/20100101 Firefox/4.0.1",
    "Opera/9.80 (Macintosh; Intel Mac OS X 10.6.8; U; en) Presto/2.8.131 Version/11.11",
    "Opera/9.80 (Windows NT 6.1; U; en) Presto/2.8.131 Version/11.11",
    "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_0) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.56 Safari/535.11",
    "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Maxthon 2.0)",
    "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; TencentTraveler 4.0)",
    "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1)",
    "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; The World)",
    "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Trident/4.0; SE 2.X MetaSr 1.0; SE 2.X MetaSr 1.0; .NET CLR 2.0.50727; SE 2.X MetaSr 1.0)",
    "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; 360SE)",
    "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Avant Browser)",
    "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1)",
    "Mozilla/5.0 (iPhone; U; CPU iPhone OS 4_3_3 like Mac OS X; en-us) AppleWebKit/533.17.9 (KHTML, like Gecko) Version/5.0.2 Mobile/8J2 Safari/6533.18.5",
    "Mozilla/5.0 (iPod; U; CPU iPhone OS 4_3_3 like Mac OS X; en-us) AppleWebKit/533.17.9 (KHTML, like Gecko) Version/5.0.2 Mobile/8J2 Safari/6533.18.5",
    "Mozilla/5.0 (iPad; U; CPU OS 4_3_3 like Mac OS X; en-us) AppleWebKit/533.17.9 (KHTML, like Gecko) Version/5.0.2 Mobile/8J2 Safari/6533.18.5",
    "Mozilla/5.0 (Linux; U; Android 2.3.7; en-us; Nexus One Build/FRF91) AppleWebKit/533.1 (KHTML, like Gecko) Version/4.0 Mobile Safari/533.1",
    "MQQBrowser/26 Mozilla/5.0 (Linux; U; Android 2.3.7; zh-cn; MB200 Build/GRJ22; CyanogenMod-7) AppleWebKit/533.1 (KHTML, like Gecko) Version/4.0 Mobile Safari/533.1",
    "Opera/9.80 (Android 2.3.4; Linux; Opera Mobi/build-1107180945; U; en-GB) Presto/2.8.149 Version/11.10",
    "Mozilla/5.0 (Linux; U; Android 3.0; en-us; Xoom Build/HRI39) AppleWebKit/534.13 (KHTML, like Gecko) Version/4.0 Safari/534.13",
    "Mozilla/5.0 (BlackBerry; U; BlackBerry 9800; en) AppleWebKit/534.1+ (KHTML, like Gecko) Version/6.0.0.337 Mobile Safari/534.1+",
    "Mozilla/5.0 (hp-tablet; Linux; hpwOS/3.0.0; U; en-US) AppleWebKit/534.6 (KHTML, like Gecko) wOSBrowser/233.70 Safari/534.6 TouchPad/1.0",
    "Mozilla/5.0 (SymbianOS/9.4; Series60/5.0 NokiaN97-1/20.0.019; Profile/MIDP-2.1 Configuration/CLDC-1.1) AppleWebKit/525 (KHTML, like Gecko) BrowserNG/7.1.18124",
    "Mozilla/5.0 (compatible; MSIE 9.0; Windows Phone OS 7.5; Trident/5.0; IEMobile/9.0; HTC; Titan)",
    "UCWEB7.0.2.37/28/999",
    "NOKIA5700/ UCWEB7.0.2.37/28/999",
    "Openwave/ UCWEB7.0.2.37/28/999",
    "Mozilla/4.0 (compatible; MSIE 6.0; ) Opera/UCWEB7.0.2.37/28/999",
    # iPhone 6：
    "Mozilla/6.0 (iPhone; CPU iPhone OS 8_0 like Mac OS X) AppleWebKit/536.26 (KHTML, like Gecko) Version/8.0 Mobile/10A5376e Safari/8536.25",
]
headers = {'User-Agent': random.choice(user_agent)}
url = 'https://sc.chinaz.com/tupian/shuaigetupian.html'

#滚动条缓慢滚动10次
def windowscroll():  #每次停格一秒，滚动10次。
    height=0
    #滚动条连续滚动10次
    for i in range(10):
        driver.execute_script("window.scrollTo({},{});".format(height,height+500))
        height = height + 500
        time.sleep(1)

if __name__ == '__main__':
    #拼接完成后的完整下载链接存放列表
    url_list = []
    #因为网页中的图片是动态加载的，所以这里我们使用selenium动态加载
    #浏览器驱动绝对路径
    driver = webdriver.Chrome()
    url_linklist=[]
    url_linklist.append(url)
    for i in range(1, 44):
        url = 'https://sc.chinaz.com/tupian/shuaigetupian_{}.html'.format(i + 1)
        url_linklist.append(url)

    for i in url_linklist:
        #跳转网页
        driver.get(i)
        #睡眠2秒
        time.sleep(2)

        driver.maximize_window()

        #睡眠2秒
        time.sleep(2)

        #滚动条缓慢滚动10次
        windowscroll()

        time.sleep(1)

        #获取完全加载完成的网页源码
        source_result = driver.page_source
        #对源码进行解析
        html=etree.HTML(source_result)
        #获取图片的下载路径，存如img_urls列表中
        img_urls=html.xpath('/html/body/div[3]/div[2]/div/img/@src')
        print(img_urls)

        #拼接完整的图片下载链接
        for i in range(len(img_urls)):
            full_url="http:"+img_urls[i]
            url_list.append(full_url)
            print(full_url+'\n')
    driver.quit()

#本地文件夹，目标下载位置
dir="D://spider_file//spider_image1"

#遍历完整下载链接列表，写入本地文件夹
for ur in url_list:
    # time.sleep(1)
    file_name = ur.split('/')[-1]
    path=dir + '/' + file_name
    # print(path+'\n')
    f = requests.get(ur, headers=headers)
    with open(path,'wb') as h:
        h.write(f.content)

爬取思路：1.今天的任务是想把整个网站所有页面的图片都爬下来，简单观察了一下不同网站的规律，发现他们的网址链接是有规律的，如下可发现，他们的链接末尾是依次+1（除第一页外），利用这个规律，我们通过for循环，将所有要跳转的网址写入了列表，后面涉及的相同的代码也写进for循环。其余代码和昨天差不多
https://sc.chinaz.com/tupian/shuaigetupian.html
https://sc.chinaz.com/tupian/shuaigetupian_2.html

https://sc.chinaz.com/tupian/shuaigetupian_44.html

2.今天顺便把滚动条滚动的代码写成了函数直接调用。

很早之前写的了，自己搬运一下的。