python截取全页面,Python获取网页里全部网址

from selenium import webdriver

import re

url="http://www.baidu.com/"

brower = webdriver.Firefox()

brower.get(url)

pagesoures = brower.page_source # 抓取网页源代码

restr = r'http[s]?://(?:[a-zA-Z]|[0-9]|[$-_@.&+]|[!*\(\),]|(?:%[0-9a-fA-F][0-9a-fA-F]))+' # 如果不带括号会输出全部,只要()内的数据如果政策抓取不到也许他前面有空格

rex = re.compile(restr, re.IGNORECASE)

mylist = rex.findall(pagesoures)

brower.close()

print(mylist)

data = open("D:\data.txt", 'w+')

print(mylist, file=data)

data.close()

python读入写出

python常用的读取文件函数有三种read()、readline()、readlines()

read() 一次性读全部内容

with open("test.txt", "r") as f: #打开文件

data = f.read() #读取文件

print(data)

readline() 读取第一行内容

with open("test.txt", "r") as f:

data = f.readline()

print(data)

readlines() 列表

with open("test.txt", "r") as f:

data = f.readlines()

print(data)

会出现换行

with open("test.txt", "r") as f:

for line in f.readlines():

line = line.strip('\n') #去掉列表中每一个元素的换行符

print(line)

write

with open("test.txt","w") as f:

f.write("这是个测试！") #这句话自带文件关闭功能，不需要再写f.close()

print文件中

data=open("D:\data.txt",'w+')

print('这是个测试',file=data)

data.close()

也可以用pip install requests库来进行爬取数据