import requests
from urllib.error import URLError
import os
import urllib
from urllib.parse import urlencode
headers = {'user-agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.110 Safari/537.36'}
def get_page(offset):
#解析网页
params = {
'pn': offset,
'rn': 30,
'gsm': str(hex(offset))}
url = 'https://image.baidu.com/search/acjson?tn=resultjson_com&ipn=rj&ct=201326592&is=&fp=result&queryWord=%E8%A1%97%E6%8B%8D&cl=&lm=&ie=utf-8&oe=utf-8&adpicid=&st=&z=&ic=&hd=&latest=©right=&word=%E8%A1%97%E6%8B%8D&s=&se=&tab=&width=&height=&face=&istype=&qc=&nc=&fr=&expermode=&selected_tags=' + urlencode(
params)
try:
request = requests.get(url, headers=headers)
if request.status_code == 200:
return request.json()
except:
return None
def decry(a):
#解密图片网址
str_table = {
'_z2C$q': ':',
'_z&e3B': '.',
'AzdH3F': '/', }
in_table = '0123456789abcdefghijklmnopqrstuvw'
out_table = '7dgjmoru140852vsnkheb963wtqplifca'
char_table = str.maketrans(in_table, out_table)
if True:
for key, value in str_table.items():
a = a.replace(key, value)
a = a.translate(char_table)
return a
def get_img(json):
#获取图片网址
data = json.get('data')
m = 1
if data:
for item in data:
try:
if item.get('objURL'):
image = decry(item.get('objURL'))
title = str(m)
yield{
'image': image,
'title': title, }
m += 1
except URLError as e:
print(e.reason)
def save_img(item):
#保存图片
path = os.path.join("./mypic/", item.get('title'))
if not os.path.exists(path):
os.makedirs(path)
local_image_url = item.get('image')
if local_image_url:
save_pic = path + "/" + local_image_url.split('/').pop(2)+".jpg"
urllib.request.urlretrieve(local_image_url, save_pic)
def main(offset):
json = get_page(offset)
for item in get_img(json):
print(item)
save_img(item)
if __name__ == '__main__':
for i in range(1, 3):
j = i * 30
main(offset=j)
爬虫实战5:爬取百度图片
最新推荐文章于 2024-05-27 13:31:48 发布