动漫之家-漫画爬取
鲜于凯歌
[注意]：仅作为一个示例来讨论，请不要恶意占用服务器资源，漫画在线上看的体验反而好一些
[分析]：动漫之家的反爬虫主要是靠User-Agent，加一个headers就好了。这里主要讨论一下如何获取img_urls。
分析漫画第一章第一页可以发现，<head>标签里的第一个script脚本里已经生成了这一章所有图片的链接（中间那个加密函数分析了一下，大概就是替换吧，以后有兴趣再研究），在console里输入arr_pages，果然获取了所有图片的url，补上图库链接头部 https://images.dmzj.com/ 就得到了所有图片链接。具体做法就是用BeautifulSoup或lxml拿到script后用execjs运行一下脚本，最后取出arr_pages的值就可以爬爬爬了（记得加上Referer）。
<script type="text/javascript">
var arr_img = new Array();
var page = '';
eval(function(p,a,c,k,e,d){e=function(c){return(c<a?'':e(parseInt(c/a)))+((c=c%a)>35?String.fromCharCode(c+29):c.toString(36))};if(!''.replace(/^/,String)){while(c--){d[e(c)]=k[c]||e(c)}k=[function(e){return d[e]}];e=function(){return'\\w+'};c=1};while(c--){if(k[c]){p=p.replace(new RegExp('\\b'+e(c)+'\\b','g'),k[c])}}return p}('v m=m=\'["h\\/%3%2%0%1%5%4%9%a%0%d%b%7%6%8%c-%f%i%g%3%2%0%1%5%4%6%e%k\\/%3%2%0%1%5%4%9%a%0%d%b%7%6%8%c-%f%i%g%3%2%0%1%5%4%6%e%l\\/x.j","h\\/%3%2%0%1%5%4%9%a%0%d%b%7%6%8%c-%f%i%g%3%2%0%1%5%4%6%e%k\\/%3%2%0%1%5%4%9%a%0%d%b%7%6%8%c-%f%i%g%3%2%0%1%5%4%6%e%l\\/y.j","h\\/%3%2%0%1%5%4%9%a%0%d%b%7%6%8%c-%f%i%g%3%2%0%1%5%4%6%e%k\\/%3%2%0%1%5%4%9%a%0%d%b%7%6%8%c-%f%i%g%3%2%0%1%5%4%6%e%l\\/u.j","h\\/%3%2%0%1%5%4%9%a%0%d%b%7%6%8%c-%f%i%g%3%2%0%1%5%4%6%e%k\\/%3%2%0%1%5%4%9%a%0%d%b%7%6%8%c-%f%i%g%3%2%0%1%5%4%6%e%l\\/A.j","h\\/%3%2%0%1%5%4%9%a%0%d%b%7%6%8%c-%f%i%g%3%2%0%1%5%4%6%e%k\\/%3%2%0%1%5%4%9%a%0%d%b%7%6%8%c-%f%i%g%3%2%0%1%5%4%6%e%l\\/z.j","h\\/%3%2%0%1%5%4%9%a%0%d%b%7%6%8%c-%f%i%g%3%2%0%1%5%4%6%e%k\\/%3%2%0%1%5%4%9%a%0%d%b%7%6%8%c-%f%i%g%3%2%0%1%5%4%6%e%l\\/B.j","h\\/%3%2%0%1%5%4%9%a%0%d%b%7%6%8%c-%f%i%g%3%2%0%1%5%4%6%e%k\\/%3%2%0%1%5%4%9%a%0%d%b%7%6%8%c-%f%i%g%3%2%0%1%5%4%6%e%l\\/r.j","h\\/%3%2%0%1%5%4%9%a%0%d%b%7%6%8%c-%f%i%g%3%2%0%1%5%4%6%e%k\\/%3%2%0%1%5%4%9%a%0%d%b%7%6%8%c-%f%i%g%3%2%0%1%5%4%6%e%l\\/p.j","h\\/%3%2%0%1%5%4%9%a%0%d%b%7%6%8%c-%f%i%g%3%2%0%1%5%4%6%e%k\\/%3%2%0%1%5%4%9%a%0%d%b%7%6%8%c-%f%i%g%3%2%0%1%5%4%6%e%l\\/o.j","h\\/%3%2%0%1%5%4%9%a%0%d%b%7%6%8%c-%f%i%g%3%2%0%1%5%4%6%e%k\\/%3%2%0%1%5%4%9%a%0%d%b%7%6%8%c-%f%i%g%3%2%0%1%5%4%6%e%l\\/q.j","h\\/%3%2%0%1%5%4%9%a%0%d%b%7%6%8%c-%f%i%g%3%2%0%1%5%4%6%e%k\\/%3%2%0%1%5%4%9%a%0%d%b%7%6%8%c-%f%i%g%3%2%0%1%5%4%6%e%l\\/s.j","h\\/%3%2%0%1%5%4%9%a%0%d%b%7%6%8%c-%f%i%g%3%2%0%1%5%4%6%e%k\\/%3%2%0%1%5%4%9%a%0%d%b%7%6%8%c-%f%i%g%3%2%0%1%5%4%6%e%l\\/t.j","h\\/%3%2%0%1%5%4%9%a%0%d%b%7%6%8%c-%f%i%g%3%2%0%1%5%4%6%e%k\\/%3%2%0%1%5%4%9%a%0%d%b%7%6%8%c-%f%i%g%3%2%0%1%5%4%6%e%l\\/n.j","h\\/%3%2%0%1%5%4%9%a%0%d%b%7%6%8%c-%f%i%g%3%2%0%1%5%4%6%e%k\\/%3%2%0%1%5%4%9%a%0%d%b%7%6%8%c-%f%i%g%3%2%0%1%5%4%6%e%l\\/w.j","h\\/%3%2%0%1%5%4%9%a%0%d%b%7%6%8%c-%f%i%g%3%2%0%1%5%4%6%e%k\\/%3%2%0%1%5%4%9%a%0%d%b%7%6%8%c-%f%i%g%3%2%0%1%5%4%6%e%l\\/J.j","h\\/%3%2%0%1%5%4%9%a%0%d%b%7%6%8%c-%f%i%g%3%2%0%1%5%4%6%e%k\\/%3%2%0%1%5%4%9%a%0%d%b%7%6%8%c-%f%i%g%3%2%0%1%5%4%6%e%l\\/M.j","h\\/%3%2%0%1%5%4%9%a%0%d%b%7%6%8%c-%f%i%g%3%2%0%1%5%4%6%e%k\\/%3%2%0%1%5%4%9%a%0%d%b%7%6%8%c-%f%i%g%3%2%0%1%5%4%6%e%l\\/L.j","h\\/%3%2%0%1%5%4%9%a%0%d%b%7%6%8%c-%f%i%g%3%2%0%1%5%4%6%e%k\\/%3%2%0%1%5%4%9%a%0%d%b%7%6%8%c-%f%i%g%3%2%0%1%5%4%6%e%l\\/O.j","h\\/%3%2%0%1%5%4%9%a%0%d%b%7%6%8%c-%f%i%g%3%2%0%1%5%4%6%e%k\\/%3%2%0%1%5%4%9%a%0%d%b%7%6%8%c-%f%i%g%3%2%0%1%5%4%6%e%l\\/P.j","h\\/%3%2%0%1%5%4%9%a%0%d%b%7%6%8%c-%f%i%g%3%2%0%1%5%4%6%e%k\\/%3%2%0%1%5%4%9%a%0%d%b%7%6%8%c-%f%i%g%3%2%0%1%5%4%6%e%l\\/Q.j","h\\/%3%2%0%1%5%4%9%a%0%d%b%7%6%8%c-%f%i%g%3%2%0%1%5%4%6%e%k\\/%3%2%0%1%5%4%9%a%0%d%b%7%6%8%c-%f%i%g%3%2%0%1%5%4%6%e%l\\/N.j","h\\/%3%2%0%1%5%4%9%a%0%d%b%7%6%8%c-%f%i%g%3%2%0%1%5%4%6%e%k\\/%3%2%0%1%5%4%9%a%0%d%b%7%6%8%c-%f%i%g%3%2%0%1%5%4%6%e%l\\/K.j","h\\/%3%2%0%1%5%4%9%a%0%d%b%7%6%8%c-%f%i%g%3%2%0%1%5%4%6%e%k\\/%3%2%0%1%5%4%9%a%0%d%b%7%6%8%c-%f%i%g%3%2%0%1%5%4%6%e%l\\/E.j","h\\/%3%2%0%1%5%4%9%a%0%d%b%7%6%8%c-%f%i%g%3%2%0%1%5%4%6%e%k\\/%3%2%0%1%5%4%9%a%0%d%b%7%6%8%c-%f%i%g%3%2%0%1%5%4%6%e%l\\/D.j","h\\/%3%2%0%1%5%4%9%a%0%d%b%7%6%8%c-%f%i%g%3%2%0%1%5%4%6%e%k\\/%3%2%0%1%5%4%9%a%0%d%b%7%6%8%c-%f%i%g%3%2%0%1%5%4%6%e%l\\/C.j","h\\/%3%2%0%1%5%4%9%a%0%d%b%7%6%8%c-%f%i%g%3%2%0%1%5%4%6%e%k\\/%3%2%0%1%5%4%9%a%0%d%b%7%6%8%c-%f%i%g%3%2%0%1%5%4%6%e%l\\/F.j","h\\/%3%2%0%1%5%4%9%a%0%d%b%7%6%8%c-%f%i%g%3%2%0%1%5%4%6%e%k\\/%3%2%0%1%5%4%9%a%0%d%b%7%6%8%c-%f%i%g%3%2%0%1%5%4%6%e%l\\/G.j","h\\/%3%2%0%1%5%4%9%a%0%d%b%7%6%8%c-%f%i%g%3%2%0%1%5%4%6%e%k\\/%3%2%0%1%5%4%9%a%0%d%b%7%6%8%c-%f%i%g%3%2%0%1%5%4%6%e%l\\/I.j","h\\/%3%2%0%1%5%4%9%a%0%d%b%7%6%8%c-%f%i%g%3%2%0%1%5%4%6%e%k\\/%3%2%0%1%5%4%9%a%0%d%b%7%6%8%c-%f%i%g%3%2%0%1%5%4%6%e%l\\/H.j"]\';',53,53,'91|E4|BB|E9|8B|B9|E8|A6|80|E5|A5|BA|85|E7|8A|E6|86||BC|jpg|B1|B1_ch01|pages|013|009|008|010|007|011|012|003|var|014|001|002|005|004|006|025|024|023|026|027|029|028|015|022|017|016|021|018|019|020'.split('|'),0,{}))
;
var g_comic_name = "黑之契约者-漆黑之花";
var g_chapter_name = "第01话";
var g_comic_url = "hzqyzqhzh/";
var g_chapter_url = "hzqyzqhzh/3505.shtml";
var g_current_page = 1;
var g_max_pic_count = 29;
var g_page_base = '';
var g_comic_id = res_id = '1499';
var g_chapter_id = chapter_id = '3505';
var g_comic_code = '9237261211e72bf656b9093c28f90dff';
var arr_pages = eval(pages);
var next_chapter_pages = '["h\/%E9%BB%91%E4%B9%8B%E5%A5%91%E7%BA%A6%E8%80%85-%E6%BC%86%E9%BB%91%E4%B9%8B%E8%8A%B1\/%E9%BB%91%E4%B9%8B%E5%A5%91%E7%BA%A6%E8%80%85-%E6%BC%86%E9%BB%91%E4%B9%8B%E8%8A%B1_ch02\/001.jpg","h\/%E9%BB%91%E4%B9%8B%E5%A5%91%E7%BA%A6%E8%80%85-%E6%BC%86%E9%BB%91%E4%B9%8B%E8%8A%B1\/%E9%BB%91%E4%B9%8B%E5%A5%91%E7%BA%A6%E8%80%85-%E6%BC%86%E9%BB%91%E4%B9%8B%E8%8A%B1_ch02\/002.jpg","h\/%E9%BB%91%E4%B9%8B%E5%A5%91%E7%BA%A6%E8%80%85-%E6%BC%86%E9%BB%91%E4%B9%8B%E8%8A%B1\/%E9%BB%91%E4%B9%8B%E5%A5%91%E7%BA%A6%E8%80%85-%E6%BC%86%E9%BB%91%E4%B9%8B%E8%8A%B1_ch02\/003.jpg"]';
var arr_nextchapter_pages = eval(next_chapter_pages);
var final_page_url = "/hzqyzqhzh/jump.shtml?1499_3505&fbee072bb6c4a008aae02970f932a1fc";
var sns_sys_id = '1499_3505';
var sns_view_point_token = 'fbee072bb6c4a008aae02970f932a1fc';
var is_hot_comic = false;
var is_fast_comic = true;
var server_name = 0;
var page_site_root = '/';
var res_type = 1;
</script># 部分代码示例（爬的是食灵，不是黑契）
def download_img(url):
res = requests.get(img_host + '/' + url, headers = headers, timeout = 3)
if res.status_code == 200:
res.encoding = 'UTF-8'
with open('{:s}'.format(url.split('/')[-1]), 'wb+') as f: # 用img链接最后一段命名文件，比较方便
f.write(res.content)
else:
res.raise_for_status
headers = {
'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_11_6) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/74.0.3729.131 Safari/537.36',
'Referer': 'https://manhua.dmzj.com/shiling/'
}
chapters = soup(class_ = "cartoon_online_border")[0].find_all('a', href = re.compile('/shiling'))
for chapter in chapters:
current_path = path + '/' + title + '/' + chapter.string
not os.path.exists(current_path) and os.mkdir(current_path)
os.chdir(current_path)
js = get_html(arr_url + chapter['href']).find('script')
ctx = execjs.compile(js.string) # 注意不能直接运行js，得去掉标签
imgs = ctx.eval('arr_pages')
for img in imgs:
download_img(img)连接/下载速度还行，所以没考虑异常处理
类似资料：