import re
import urllib.request
import gevent
def download(image_download, images_path,i):
headers = {"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/68.0.3440.106 Safari/537.36"}
req = urllib.request.Request(url=images_path, headers=headers)
image = urllib.request.urlopen(req)
image_content = image.read()
image_name = image_download + "/" + str(i) + ".jpg"
file = open(image_name, "wb")
file.write(image_content)
file.close()
def main():
with open("douyu.html", "r", encoding="utf-8") as f:
messages = f.read()
images_path = re.findall(r"https://.*?\.jpg", messages)
directory = "images_douyu"
i = 0
gevent_list = list()
for image_path in images_path:
i += 1
gevent_list.append(gevent.spawn(download,directory, image_path, i))
gevent.joinall(gevent_list)
if __name__ == "__main__":
main()