最近刚刚学习了正则表达式,于是立刻用正则表达式爬取了包图网教师节海报
from urllib import request
import re
import os.path
headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/92.0.4515.159 Safari/537.36'
}
#定义一个url拼接的函数
def url_splice(page):
url = 'https://ibaotu.com/guanggao/1-106-0-1206-0-' + str(page) +'.html'#找到每页教师节图片url的共同点
return url
#定义一个获取原网页的类
class Page_Text(object):
def __init__(self, url , headers): #初始化,传入url和headers
self.url = url
self.headers = headers
self.pattern = '<dt><a href="(.*?)" target="_blank" data-id="[0-9]*".*?alt="(.*?)".*?</a>.*?</dt>' #初始化正则表达式规则
def get_page_text(self): #获取原网页源代码
req = request.Request