在爬虫中如何添加多线程并且异步执行,需要添加线程互斥锁吗?
求添加基于下方代码的多线程爬虫,以及注意事项(知识点)
本人自学的小小白,多谢
import requests
import re
class Dytt_pa(object):
def __init__(self):
self.file_dict = {}
self.pagecontent = ''
def get_page(self,url='https://www.dytt8.net/html/gndy/dyzz/list_23_1.html'): # 定义缺省url为xxx
"""获取电影列表网页源码"""
headers = {"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/76.0.3809.62 Safari/537.36"}
req = requests.get(url,headers=headers)
req.encoding = 'GBK'
self.pagecontent = req.text # 运行之后得到get_page的结果,返回新内容
def get_film_link(self):
"""将迅雷下载地址与电影名保存到字典中"""
file_list = re.findall(r'<a href="(.*)" class="ulink">(.*)</a>',self.pagecontent) # 得到25个(半个电影link和电影名)的list
for film_link,film_name in file_list:
page_heard = "https://www.dytt8.net"
film_link = page_heard + film_link # list中的完整的电影link
self.get_page(url=film_link) # 电影详情页源码
xun_lei = re.search(r'<td style=".*" bgcolor=".*"><a href="(.*)">ftp',self.pagecontent).group(1) # 正则出迅雷下载地址
self.file_dict[film_name] = xun_lei
def start(self):
num = int(input("请输入你要下载几页:"))
for numa in range(1,num+1):
print("正在下载第%d页,请稍后"%numa)
self.get_page(url='https://www.dytt8.net/html/gndy/dyzz/list_23_%d.html'%numa)
self.get_film_link()
print("已下载完第%d页."%numa)
for a, b in self.file_dict.items():
print("%s|%s" % (a, b))
if __name__ == '__main__':
woyaoxiadiany = Dytt_pa()
woyaoxiadiany.start()