python爬虫项目-一见倾心壁纸

目录

一、利用正则表达式

二、利用beautifulsoup

---

方法1

import re
import os
import urllib
import urllib.request

def getHtml(url):
    page = urllib.request.urlopen(url)
    html = page.read()
    return html

def getImage(html,x):
    #https://mmbiz.qpic.cn/mmbiz_jpg/ib55rg6wzUc3B16KIY3uU53nkcTTDic8uEA4WWBPaHJ8LpibvAnkpS2FZtyjrv7w7dbEeNrhfvPuuyReNAxsLdgJA/640?wx_fmt=jpeg
    #https://mmbiz.qpic.cn/mmbiz_jpg/ib55rg6wzUc3B16KIY3uU53nkcTTDic8uEHqocI7r86nehl2NeForAqvcTiaEAIuWjTWPKNXnnXIPuUuqnuJeFKYw/640?wx_fmt=jpeg
    #此处正则为重点
    reg = 'data-src="(.*?)"'
    image = re.compile(reg)
    imlist = re.findall(reg,html.decode('utf-8'))

    print(imlist)
    for i in imlist:
        print(i)
        print(x)
        # 下载内容与.py一起
        #urllib.request.urlretrieve(i,'%s.jpg' % x)
        # 下载位置自定义
        urllib.request.urlretrieve(i, r'F:desktop爬取的图片\%s.jpg' % x)
        x +=1
    return x
# -------------递归创建的目录-----------
path = r"F:desktop爬取的图片"
if not os.path.exists(path):
    os.makedirs(path)
#-----------存储目录创建结束------------
# main 下载结果与此.py文件在同一目录'
x=1
url = 'https://mp.weixin.qq.com/s/MVDcn0O3093OlIhMYkqBIA'
html = getHtml(url)
x = getImage(html,x)
print('下载完成')

方法2：BeautifulSoup 避免写正则表达式(因为不会）

  

import os
import requests
import urllib.request
from bs4 import BeautifulSoup
#微信下载图片的网址
url = "https://mp.weixin.qq.com/s/cm3Bua0UM1jbZnr2de7TWg"
r = requests.get(url)
demo = r.text
soup = BeautifulSoup(demo, "html.parser")
piclist = []
for link in soup.find_all('img'):
    link_list = link.get('data-src')
    if link_list != None:
        piclist.append(link_list)
# print(piclist)
# print(type(link_list))
# -------------递归创建的目录-----------
path = r"F:desktop爬取的图片"
if not os.path.exists(path):
    os.makedirs(path)
#-----------存储目录创建结束------------
x = 0
for http in piclist:
    print(http)
    filesavepath = r'F:desktop爬取的图片\%s.jpg' % x
    urllib.request.urlretrieve(http, filesavepath)
    x += 1
    print('正在保存第{:.0f}张图片'.format(x))
print('下载完成')