该楼层疑似违规已被系统折叠 隐藏此楼查看此楼
import requests
from requests.exceptions import RequestException
import re
def get_one_page(url):
headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) '
+ 'Chrome/55.0.2883.87 UBrowser/6.2.3831.602 Safari/537.36'
}
try:
respones = requests.get(url, headers=headers)
if respones.status_code == 200:
return respones.text
return None
except RequestException:
return None
def parse_one_age(html):
pattern = re.compile('
.*?data-src="(.*?)".*?', re.S)items = re.findall(pattern, html)
for item in items:
yield {
item
}
def download_pic(each):
i = 0
for pic_url in each:
print(pic_url)
pic = requests.get(pic_url)
file_path = open('D:\\img_python\\%s.jpg' % i, 'wb')
file_path.write(pic.content)
i = i + 1
def main():
url = 'http://maoyan.com/board/4?'
html = get_one_page(url)
for item in parse_one_age(html):
print(item)
download_pic(item)
if __name__ == '__main__':
main()