复制代码- import os
import requests
import threading
from faker import Faker
faker = Faker(locale='zh_CN')
from pyquery import PyQuery as pq
'''下载单本漫画'''
def get_doc(url): #返回pyquery对象
headers = {'User-Agent':faker.user_agent()} #用随机UA
response = requests.get(url,headers=headers)
html = response.text
doc = pq(html)
return doc
def make_file(file_path,file_name): #目标路径和文件夹名
if os.path.exists(os.path.join(file_path,file_name)): #判断是否存在目标文件夹
return os.path.join(file_path,file_name)
else: #没有就创建
os.makedirs(os.path.join(file_path,file_name))
return os.path.join(file_path,file_name)
def save_img_noreferer(path,src):
headers = {'User-Agent':faker.user_agent()}
try:
response = requests.get(src,headers=headers) #有的时候仍然会出现UA反爬虫，跳过
except:
pass
else:
if response.status_code == 200 or response.status_code == 206:
name = src.split('/')[-1] #图片名称默认为存在服务器里的名称
path = os.path.join(path,name)
with open(path,'wb') as f:
f.write(response.content)
elif response.status_code == 522: #状态码522，重试
save_img_noreferer(path,src)
elif response.status_code == 404: #状态码404，可能是src图片格式问题
save_img_noreferer(path,src.replace('jpg','png'))
else: #为防止错误，跳过
pass
glock = threading.Lock()
def save_imgs(srcs,path): #多线程,配合save_img_noreferer()使用
while True:
glock.acquire()
if len(srcs) ==0:
glock.release()
break
else:
src = srcs.pop()
glock.release()
save_img_noreferer(path,src) #记得修改path
def main():
url_main = input('请输入下载漫画的地址：')
num = url_main.split('/')[-1].split('o')[0] #漫画代码
doc = get_doc(url_main)
page = doc('.ld_box > div:nth-child(2) > .ld_body').text().split(' ')[0] #漫画页码
title = doc('#comicdetail > h1').text()+'id='+num+'page='+page #漫画标题
src_format = doc('>img')[0].items()[2][1].split('/')[2] #服务器地址
print('当前漫画服务器地址为：'+src_format+',数字越大下载越慢，请耐心等待')
pic_format = 'jpg' #默认图片格式
list_1 = ['\\','/',':','*','?','"','<','>','|'] #去除漫画名中的非法字符
for i in list_1:
if i in title:
title = title.replace(i,'')
print('开始下载：'+title)
path = make_file('./本子',title)
print(title+'用有'+page+'页')
srcs = []
for i in range(1,int(page)+1):
src = 'https://'+src_format+'/galleries/'+num+'/'+str(i)+'.'+pic_format #图片src
srcs.append(src)
for _ in range(64): #64个线程
consumer = threading.Thread(target=save_imgs,args=[srcs,path,])
consumer.start()
if __name__ == '__main__':
main()
|
学到了
