from bs4 import BeautifulSoup
import requests
import os
######對風景進行爬出操做
r = requests.get("http://699pic.com/sousuo-218808-13-1-0-0-0.html")
fengjing = r.content
soup = BeautifulSoup(fengjing,"html.parser")
#print(soup.prettify())
#找出全部class標籤
images = soup.find_all(class_="lazy")
print(images)
for item in images:
try:
jpg_url = item["data-original"]
title = item["title"]
print(title)
print(jpg_url)
print("")
#保存圖片
with open(os.getcwd()+"\\jpg"+title+".jpg","wb") as f:
f.write(requests.get(jpg_url).content)
except Exception as e:
pass
另外爬蟲Blog以下程序:html
from bs4 import BeautifulSoup
import requests
#r = requests.get("https://www.cnblogs.com/Teachertao/")
# 請求首頁後獲取整個 html 界面
blog = r.content
#print(blog)
#用html.parser解析出html
soup = BeautifulSoup(blog,"html.parser")
# prettify()能夠自動解析爲html格式
print(soup.prettify())
#獲取全部的class屬性爲"block_title",返回Tag類
time = soup.find_all(class_="block_title")
#print(time)
db = [item for item in time]
print(db)
# 獲取title
title = soup.find_all(class_="posttitle")
print(title)
#獲取摘要
desc = soup.find_all(class_="c_b_p_desc")
print(desc)
for item in desc:
# tag 的 .contents 屬性能夠將 tag 的子節點以列表的方式輸出
print(item)
########標籤以下截圖:
########運行結果展現post