# 创建一个下载美女图片的方法
from urllib import request, parse
import gevent
import gevent.monkey
gevent.monkey.patch_all() # 把所有的耗时转化成gevent的函数
import re
def read_img():
# 抓取网页内容-发送报头-1
url = "https://www.douyu.com/directory/game/yz"
send_headers = {
'Host': 'www.douyu.com',
'User-Agent': 'Mozilla/5.0 (Windows NT 6.2; rv:16.0) Gecko/20100101 Firefox/16.0',
'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
'Connection': 'keep-alive'
}
# url = "http://httpbin.org/post"
# headers = {
# # 伪装一个火狐浏览器
# "User-Agent": 'Mozilla/4.0 (compatible; MSIE 5.5; Windows NT)',
# "host": 'httpbin.org'
# }
dict = {
"name": "oldyang"
}
data = bytes(parse.urlencode(dict), encoding="utf8")
req = request.Request(url=url, headers=send_headers, method="GET")
response = request.urlopen(req)
content = response.read().decode("utf-8")
print(content)
# 正则
reg = r'data-original="(https://.+\.jpg)"' # 定义一个正则来匹配页面当中的图片
imgre = re.compile(reg) # 为了让正则更快,给它来个编译
imglist = re.findall(imgre, content)
return imglist
def write_img(file_name, image_url):
# 读取所有图片
req = request.urlopen(image_url)
content = req.read()
# 写到文件中
with open("./images/%s.jpg" % file_name, 'wb') as f:
f.write(content)
def main():
images = read_img()
for image_url in images:
spawns.append(gevent.spawn(write_img, num, image_url))
num += 1
# 使用协程进行数据抓取
gevent.joinall(spawns)
if __name__ == '__main__':
main()
from urllib import request, parse
import gevent
import gevent.monkey
gevent.monkey.patch_all() # 把所有的耗时转化成gevent的函数
import re
def read_img():
# 抓取网页内容-发送报头-1
url = "https://www.douyu.com/directory/game/yz"
send_headers = {
'Host': 'www.douyu.com',
'User-Agent': 'Mozilla/5.0 (Windows NT 6.2; rv:16.0) Gecko/20100101 Firefox/16.0',
'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
'Connection': 'keep-alive'
}
# url = "http://httpbin.org/post"
# headers = {
# # 伪装一个火狐浏览器
# "User-Agent": 'Mozilla/4.0 (compatible; MSIE 5.5; Windows NT)',
# "host": 'httpbin.org'
# }
dict = {
"name": "oldyang"
}
data = bytes(parse.urlencode(dict), encoding="utf8")
req = request.Request(url=url, headers=send_headers, method="GET")
response = request.urlopen(req)
content = response.read().decode("utf-8")
print(content)
# 正则
reg = r'data-original="(https://.+\.jpg)"' # 定义一个正则来匹配页面当中的图片
imgre = re.compile(reg) # 为了让正则更快,给它来个编译
imglist = re.findall(imgre, content)
return imglist
def write_img(file_name, image_url):
# 读取所有图片
req = request.urlopen(image_url)
content = req.read()
# 写到文件中
with open("./images/%s.jpg" % file_name, 'wb') as f:
f.write(content)
def main():
images = read_img()
spawns = list()
num = 0for image_url in images:
spawns.append(gevent.spawn(write_img, num, image_url))
num += 1
# 使用协程进行数据抓取
gevent.joinall(spawns)
if __name__ == '__main__':
main()