要爬取的内容:
具体的代码:
# encoding: utf-8
"""
@version: 0.1
@author:
@site:
@software: PyCharm
@file: emoticonDemo.py
@time: 2020-05-29 9:17
"""
import requests
import re
# 表情包地址
# https://qq.yh31.com/zjbq/2920180.html
# 表情图片地址
# https://qq.yh31.com/tp/Photo7/ZJBQ/20101/201001211740218681.gif
# 第一步,找到所要爬取图片的地址
"""
1.请求目标网站
2.匹配不同图片地址(url)
3.找到所要爬取图片的地址
"""
def get_urls(url):
# 1.请求目标网站
response = requests.get(url)
# 2.通过正则来匹配不同图片地址(url)
"""
# 每张图片共有内容保留,不同的内容用.*?来匹配
# .*:表示匹配任意数量不换行的字符
# ?:表示尽可能匹配最短的字符
r'<img border="0" alt="" src="/tp/Photo7/ZJBQ/20099/200909291701134159.gif">'
"""
url_add = r'img.*? src="(.*?)"'
# url_add = r'img border="0".?* src="(.*?)"'
# print(url_add)
# 3.找到所要爬取图片的地址
url_list = re.findall(url_add, response.text)
# print(url_list)
return url_list
# 第二步,根据凭借完整的地址,下载图片数据
def get_gif(url, name):
# 1.请求要爬取图片的url
response = requests.get(url)
# 2.下载数据,保存到路径下 E:\02_python3.5\workspace\pypc\pc_demo\
with open('E:\\02_python3.5\\workspace\\pypc\\pc_demo\\gif_dir\{}'.format(name), 'wb') as ft:
ft.write(response.content)
if __name__ == '__main__':
url = 'https://qq.yh31.com/zjbq/2920180.html'
url_list = get_urls(url)
# 把列表当中的数据提取,并拼接成完整的图片url地址
for url in url_list:
# print(url)
gif_name = url[int(url.rfind('/')) + 1:]
# print(url[int(url.rfind('/')) + 1:])
# print(gif_name)
com_url = 'https://qq.yh31.com' + url
print(com_url)
#调用下载图片函数
get_gif(com_url, gif_name)
爬取结果: