|
马上注册,结交更多好友,享用更多功能^_^
您需要 登录 才可以下载或查看,没有账号?立即注册
x
- # coding = utf-8
- import re
- import gevent
- from gevent import monkey, pool
- import time, random
- import urllib.request
- monkey.patch_all()
- def downloader_img(img_url, img_name):
- """下载图片"""
- req = urllib.request.urlopen(img_url)
- img_content = req.read()
- # 下载图片保存
- with open(r"/home/python/Desktop/01_Python基础/day03/正则表达式/photo/mm%s" % img_name, "wb") as f:
- f.write(img_content)
- time.sleep(random.random())
- def main():
- p1 = pool.Pool(10) # 加入协程
- # 读取文件
- locals_addr = r"/home/python/Desktop/01_Python基础/day03/正则表达式/1.txt"
- url_txt = open(locals_addr, "r", encoding=" utf-8")
- url_content = url_txt.read()
- jpg_lists = re.findall(r"https://.*?\.jpg", url_content) # 正则匹配网页的有效地址
- num = 0
- list1 = [] # 定义一个列表用来存网址
- # 遍历图片列表
- for j in jpg_lists:
- list1.append(gevent.spawn(downloader_img, j, "%d.jpg" % num))
- num += 1
- gevent.joinall(list1)
- if __name__ == '__main__':
- main()
复制代码
# coding = utf-8
import re
import gevent
from gevent import monkey, pool
import time, random
import urllib.request
monkey.patch_all()
def downloader_img(img_url, img_name):
"""下载图片"""
req = urllib.request.urlopen(img_url)
img_content = req.read()
# 下载图片保存
with open(r"/home/python/Desktop/01_Python基础/day03/正则表达式/photo/mm%s" % img_name, "wb") as f:
f.write(img_content)
time.sleep(random.random())
def main():
p1 = pool.Pool(10) # 加入协程
# 读取文件
locals_addr = r"/home/python/Desktop/01_Python基础/day03/正则表达式/1.txt"
url_txt = open(locals_addr, "r", encoding=" utf-8")
url_content = url_txt.read()
jpg_lists = re.findall(r"https://.*?\.jpg", url_content) # 正则匹配网页的有效地址
num = 0
list1 = [] # 定义一个列表用来存网址
# 遍历图片列表
for j in jpg_lists:
list1.append(gevent.spawn(downloader_img, j, "%d.jpg" % num))
num += 1
gevent.joinall(list1)
if __name__ == '__main__':
main()
我们需要用一个txt文本保存网页源代码,然后读取里面的数据。
|
|