1.通过requests模块中的get方法获取整张页面信息。通过正则表达式,进行筛选。获得需要的数据,并进行持久化存储。
2.完整代码
# 使用re模块爬取糗事百科里面的图片内容
import requests
import re
import os
headers = {
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/96.0.4664.110 Safari/537.36"
}
if not os.path.exists("./qiushiLibs02"):
os.mkdir("./qiushiLibs02")
ex = '<div class="thumb">.*?<img src="(.*?)" alt.*?</div>'
url = "https://www.qiushibaike.com/imgrank/"
new_url = url+"page/2/"
for num in range(1,5):
new_url = url + f"page/{num}/"
print(new_url)
resp = requests.get(url=new_url,headers=headers)
# 获取整张页面的信息
page_text = resp.text
# 正则筛选出需要的内容
img_src_list = re.findall(ex,page_text,re.S)
for i in img_src_list:
img_src = "http:"+i
img_name = img_src.split("/")[-1]
img_path = "./qiushiLibs02/"+img_name
#进行访问下载
img_data = requests.get(url=img_src,headers=headers).content
with open(img_path,"wb") as fp:
fp.write(img_data)
print(img_name,"下载完成!")
3.注意事项
?
|