小白爬虫第一弹之抓取妹子图【更新版】
最近对爬虫感兴趣，参考了 http://cuiqingcai.com/3179.html 这篇文章，琢磨的小试身手，但是按照原文发现图片下载下来全是打不开的图片，这不是我想要的啊，尝试直接把图片的链接在浏览器中打开，发现已经看过的没有问题，新打开的就不行了，一直怀疑是在cookie方面做了文章，在request里也确实发现了有两个cookie的身影，但就是怎么找也找不到这两个cookie怎么来的，一度想放弃，爬个别的站算了，对妹子们的不舍还是又坚持研究了半天，在浏览器里的抓包工具里一直查看各种参数，做各种尝试，发现了一点门道，原来请求图片的时候需要增加一个参数，具体看代码吧，运行后中途连接被切断了，遂又增加了ua随机替换的方法，不废话了，代码如下：
import requests from bs4 import BeautifulSoup import os import urllib import random class mzitu(): def all_url(self, url): html = self.request(url) all_a = BeautifulSoup(html.text, 'lxml').find('div', class_='all').find_all('a') for a in all_a: title = a.get_text() if title == '早期图片': continue print(u'开始保存：', title) path = str(title).replace("?", '_') if not self.mkdir(path): ##跳过已存在的文件夹 print(u'已经跳过：', title) continue href = a['href'] self.html(href) def html(self, href): html = self.request(href) max_span = BeautifulSoup(html.text, 'lxml').find('div', class_='pagenavi').find_all('span')[-2].get_text() for page in range(1, int(max_span) + 1): page_url = href + '/' + str(page) self.img(page_url) def img(self, page_url): img_html = self.request(page_url) img_url = BeautifulSoup(img_html.text, 'lxml').find('div', class_='main-image').find('img')['src'] self.save(img_url,page_url) def save(self, img_url, page_url): name = img_url[-9:-4] try: img = self.requestpic(img_url,page_url) f = open(name + '.jpg', 'ab') f.write(img.content) f.close() except FileNotFoundError: ##捕获异常，继续往下走 print(u'图片不存在已跳过：', img_url) return False def mkdir(self, path): ##这个函数创建文件夹 path = path.strip() isExists = os.path.exists(os.path.join("D:\mzitu", path)) if not isExists: print(u'建了一个名字叫做', path, u'的文件夹！') os.makedirs(os.path.join("D:\mzitu", path)) os.chdir(os.path.join("D:\mzitu", path)) ##切换到目录 return True else: print(u'名字叫做', path, u'的文件夹已经存在了！') return False def requestpic(self, url, Referer): ##这个函数获取网页的response 然后返回 user_agent_list = [ \ "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/22.0.1207.1 Safari/537.1" \ "Mozilla/5.0 (X11; CrOS i686 2268.111.0) AppleWebKit/536.11 (KHTML, like Gecko) Chrome/20.0.1132.57 Safari/536.11", \ "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.6 (KHTML, like Gecko) Chrome/20.0.1092.0 Safari/536.6", \ "Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.6 (KHTML, like Gecko) Chrome/20.0.1090.0 Safari/536.6", \ "Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/19.77.34.5 Safari/537.1", \ "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/536.5 (KHTML, like Gecko) Chrome/19.0.1084.9 Safari/536.5", \ "Mozilla/5.0 (Windows NT 6.0) AppleWebKit/536.5 (KHTML, like Gecko) Chrome/19.0.1084.36 Safari/536.5", \ "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1063.0 Safari/536.3", \ "Mozilla/5.0 (Windows NT 5.1) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1063.0 Safari/536.3", \ "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_8_0) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1063.0 Safari/536.3", \ "Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1062.0 Safari/536.3", \ "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1062.0 Safari/536.3", \ "Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1061.1 Safari/536.3", \ "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1061.1 Safari/536.3", \ "Mozilla/5.0 (Windows NT 6.1) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1061.1 Safari/536.3", \ "Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1061.0 Safari/536.3", \ "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/535.24 (KHTML, like Gecko) Chrome/19.0.1055.1 Safari/535.24", \ "Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/535.24 (KHTML, like Gecko) Chrome/19.0.1055.1 Safari/535.24" ] ua = random.choice(user_agent_list) headers = {'User-Agent': ua,"Referer":Referer} ##较之前版本获取图片关键参数在这里 content = requests.get(url, headers=headers) return content def request(self, url): ##这个函数获取网页的response 然后返回 headers = {'User-Agent': "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/22.0.1207.1 Safari/537.1"} content = requests.get(url, headers=headers) return content Mzitu = mzitu() ##实例化 Mzitu.all_url('http://www.mzitu.com/all') ##给函数all_url传入参数 你可以当作启动爬虫（就是入口） print(u'恭喜您下载完成啦！')
感谢前人们的无私分享， 感谢 http://cuiqingcai.com/ ， 感谢mzitu的站长提供给我们这么多的优质妹子。
