Python 爬取堆糖图片

import requests,json,urllib.parse
import threading
threading_lock=threading.BoundedSemaphore(value=10)#设置最大线程

def get_page(url):
    page=requests.get(url)
    page=page.content
    page=page.decode('utf-8')
    return page

def pages_from_duitang(label):
    pages=[]
    url = 'https://www.duitang.com/napi/blog/list/by_search/?kw={}&type=feed&start={}&limit=100'
    label=urllib.parse.quote(label)
    for index in range(0,3000,100):
        page_url=url.format(label,index)
        print(page_url)
        page=get_page(page_url)
        pages.append(page)
    return pages



def findall_page(page,startpaet,endstart):
    all_strat=[]
    end=0
    while page.find(startpaet,end) != -1:
        start=page.find(startpaet,end)+len(startpaet)
        end=page.find(endstart,start)
        string=page[start:end]
        all_strat.append(string)
    return  all_strat

def pic_urls_from_pages(pages):
    pic_urls=[]
    for page in pages:
        urls=findall_page(page,'"path":"','"')
        pic_urls.extend(urls)

    return pic_urls

def download_pics(url,name):
    r=requests.get(url)
    path=r'C:\Users\Administrator\Desktop\爬取堆糖图片\pics\\'+str(name)+ '.jpg'
    with open(path,'wb') as f:
        f.write(r.content)
    threading_lock.release()
def main(label):
    pages=pages_from_duitang(label)
    pic_urls=pic_urls_from_pages(pages)
    name=0
    for url in pic_urls:
        name+=1
        threading_lock.acquire()
        print('正在下载第{}张图片'.format(name))
        t=threading.Thread(target=download_pics,args=(url,name))
        t.start()
        #download_pics(url,name)



main('表情包')