一拳超人 下载
本文系原创，禁止转载
图片来源：突袭网
话说打破热血动漫常用套路的神作，莫过于我们的光头漫画，真正实现开局999级，见人就砍，主宰整个世界的传奇，然而这部神作其实有两个版本，一个是翻拍成动画的村田版，另一个才是真正的原作——one版，原作者就是底下这位one老贼
图片来源:搜狐
咳咳，不对，是one老师！而这部作品就跟主角一样，诞生的太过于随意，所以画风长这样
还有这样
简直可以用毫无人性来描述了好么，更残忍的事实是：
一拳超人是ONE老师的随手练笔之作，而灵能才是ONE老师的认真画作。
不过如此随意的漫画一点都不让人失望的好吗！作为资深拳迷，向one老师致敬，因为你实现了万千屌丝日夜幻想的逆袭梦，所以我用python将原作漫画全部下载都我电脑上了，特此将者福利送给在座的各位，（不过我希望你们能够不要去改动源码，因为加了多线程，在速度上已经最快了，所以我特意放慢了爬的速度，为了防止网站被弄崩溃，随意希望大家能够让后来者也能用上，不然又要搞反扒，很累人的好伐！）
import requests
import time
import imp
import re
import sys
imp.reload(sys)
import os
import multiprocessing
class One_Punch_Man_Spider(object):
"""初始化地址和请求头"""
def __init__(self):
self.headers = {'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Wi\
n64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/74.\
0.3729.108 Safari/537.36'}
self.s = requests.Session()
self.url = "https://www.cartoonmad.com/comic/5035.html"
"""拉需求"""
def request_pull(self,url):
try:
response = self.s.get(url,headers=self.headers,timeout=5)
return response
except Exception as e:
print(e)
"""图片下载"""
def picture_download(self,charpter_maxpages):
try:
for charpter_maxpage in charpter_maxpages:
self.filebox_create(charpter_maxpage[0])
for page in range(1,int(charpter_maxpage[1])+1):
url_base = "http://web.cartoonmad.com/home75488/5035/"
url = f"{url_base}{charpter_maxpage[0]}/{page:0>3}.jpg"
headers = {'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Wi\
n64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/74.\
0.3729.108 Safari/537.36'}
print(url)
time.sleep(3)
response = self.s.get(url,headers = headers)
if response:
with open(f'E:\一拳超人漫画\{charpter_maxpage[0]}\第{page}页.png',"wb") as f:
f.write(response.content)
else:
print("没有响应")
sys.exit()
except FileExistsError as e:
print(e)
"""文件夹创建"""
def filebox_create(self,charpter):
try:
os.makedirs(f"E:\一拳超人漫画\{charpter}")
except FileExistsError:
pass
"""章节和最大页解析"""
def charpter_maxpage_url_parse(self):
response = self.request_pull(self.url)
if response:
response.encoding ="big5"
pattern_charpter_maxpage = re.compile(r"""(
<a\s+href=\W{1}\w+\W{1}\d+\.\w+\s+.*?>[\u4e00-\u9fa5]+\s+(\d+)\s+[\u4e00-\u9fa5]+</a>.*?font.*?\((\d+)[\u4e00-\u9fa5]+\)
)""",re.VERBOSE|re.S)
items = re.findall(pattern_charpter_maxpage,response.text)
items_list_all = [item[1:] for item in items]
num_divide = len(items_list_all)//3
items_new_0 = [items_list_all.pop(0) for i in range(0,num_divide+1)]
items_new_1 = [items_list_all.pop(0) for i in range(0,num_divide+1)]
return [items_new_0,items_new_1,items_list_all]
else:
pass
if __name__=="__main__":
one_punch_man_cartoon_downloader = One_Punch_Man_Spider()
charpter_maxpages = one_punch_man_cartoon_downloader.charpter_maxpage_url_parse()
# for i in charpter_maxpages:
# for h in i:
# print(i)
p = multiprocessing.Pool(3)
p.map(one_punch_man_cartoon_downloader.picture_download,charpter_maxpages)
喜欢我就关注我，谢谢！