python 爬取妹子图

从爬取一张图开始，到爬取某系列图片，再到你想爬取多少页就爬取多少页，这几天真是挫折多多。代码看的出来写的比较糟糕，有很多能够优化处理的地方，等能力提高了，对python理解更深时再回来修改，继续加油！
以下是完整的爬取代码：

import requests
import re

def getHtmlText(url,header={'User-Agent': 'Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/71.0.3578.98 Safari/537.36'}):            # 获取网页
    try:
        html = requests.get(url,headers=header)
        html.raise_for_status()
        html.encoding = html.apparent_encoding  
        return html
    except:
        return print("产生异常")

def getetaddress(nums):                     # 得到每个主题的地址，并返回一个地址列表addlist
    pagelist = []
    for i in range(nums):
        i += 1
        url1 = "https://www.mzitu.com/page/"+ str(i)
        html1 = getHtmlText(url1)
        pagelist.append (re.findall(r'<li><a href="(.*?)"', html1.text))	# 每一页的主题地址组成为一列表，这些列表然后再组成一个列表
        # re.findall()返回list，r"()" list的元素为这里面括号匹配到的内容，没有括号就全返回，注意特殊字符记得加'\'
    addlist = []
    for i in range(len(pagelist)):
        for j in range(len(pagelist[i])):
            addlist.append(pagelist[i][j])
    return addlist          # 处理成没有复合的列表

def gettoalpage(urladd):               # 传入某个主题地址“urladd”，并得到该系列下所有地址,通过列表ealist返回
    html2 = getHtmlText(urladd)
    p = re.findall(r'…</span><a href=\'.*?\'><span>([\d]*?)</span></a>',html2.text)     # 得到某主题的页数，便于后面形成图片地址
    p = int(p[0])
    # 得到每页地址
    ad = re.findall(r'<img src="(https://i.meizitu.net/.*?)\.jpg" alt=".*?" width="[\d]*?" height="[\d]*?" /></a></p>',html2.text)
    ad = ad[0][:-2]
    ealist = []
    for i in range(p):
        i += 1
        url2 = ad + str(i).zfill(2) +".jpg"
        ealist.append(url2)
    return ealist

def downpics(ealist):                         # 传入系列地址，进行单个系列下所有图片的保存
    for line in ealist:
        try:
        	html3 = getHtmlText(line,header={'User-Agent': 'Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/71.0.3578.98 Safari/537.36',"Referer" : "https://www.mzitu.com/"})			# header中加入Referer，搞定防盗链
        	h = line[22:-4].split('/')
        	with open("F://meizitu//" + h[0] + h[1] + h[2] + ".jpg","wb") as f:             # 保存文件时不能有“/”，我的F盘下先创建了一个‘meizitu’文件夹
            	f.write(html3.content)
            	print("正在保存%s..."%line)
         except:
         	return "异常"			# 某个图片报错，不影响后续爬取

def main():
    nums = int(input("请输入你想下载的页数："))
    print("好的\n\n别着急，马上开始...")
    addlist = getetaddress(nums)
    for urls in addlist:
        ealist = gettoalpage(urls)
        downpics(ealist)
    print("恭喜顺利完成爬取")

main()

注意：需要在F盘下先创建一个叫meizitu的文件夹。
这个完整的爬取代码就在这里结束了。

继续附上爬取某一系列的图片时所写代码：

import requests
import re

def getHtmlText(url):
    try:
        html = requests.get(url,headers = header)
        html.raise_for_status()
        html.encoding = html.apparent_encoding  
        return html
    except:
        return print("产生异常")

def savepics(html,pic):
    with open("F://meizitu//" + str(pic) +".jpg","wb") as f:
        f.write(html.content)
        print("正在保存第%d张..."%pic)
        
header = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/50.0.2661.102 UBrowser/6.1.2107.204 SafarMozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/71.0.3578.98 Safari/537.36',"Referer" : "http://www.mzitu.com/",'Host' : 'i.meizitu.net'}
for pic in range(40):
    pic += 1
    url = "https://i.meizitu.net/2018/11/26d"+ str(pic).zfill(2) +".jpg"
    html = getHtmlText(url)
    savepics(html,pic)
print("爬取完成")