在上次爬取信息的基础上下载图片。
下载挺容易的
在封面命名上画了大笔时间。。。。。
import requests
import bs4
from bs4 import BeautifulSoup
import re
url = 'http://maoyan.com/board/4'
path = 'C://Users//谢迎超//Desktop//download//'
header = {
'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8',
'Accept-Encoding': 'gzip, deflate',
'Accept-Language': 'zh-CN,zh;q=0.9',
'Cache-Control': 'max-age=0',
'Connection': 'keep-alive',
'Host': 'maoyan.com',
'Referer': 'http://maoyan.com/board',
'Upgrade-Insecure-Requests': '1',
'User-Agent': 'Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.349'
}
def GetText(url, header, offset):
# get网页源代码,猫眼电影榜每十个一夜通过params来切换页码,每一页的URL的不同在于“offset=0”,构造头模拟浏览器,猫眼disallow一般的爬虫。
try:
r = requests.get(url, params='offset=' + offset, headers=header)
r.raise_for_status()
r.encoding = r.apparent_