爬虫之 百度图片

爬虫之 百度图片

http://image.baidu.com/search/index?ct=201326592&cl=2&st=-1&lm=-1&nc=1&ie=utf-8&tn=baiduimage&ipn=r&rps=1&pv=&fm=rs7&word=风景

import re
import os
import time
import requests

if not os.path.exists('百度图片'):
    os.mkdir('百度图片')

# 获取所有图片
response = requests.get(
    'http://image.baidu.com/search/index?ct=201326592&cl=2&st=-1&lm=-1&nc=1&ie=utf-8&tn=baiduimage&ipn=r&rps=1&pv=&fm=rs7&word=风景')
data = response.text
img_desc_dics = re.findall("app.setData(('imgData.*?));", data, re.S)[0]
img_desc_dics = eval(str(img_desc_dics))

# 获取所有图片的数据
img_datas = img_desc_dics[1]['data']
count = 0
for img_data in img_datas:
    # 获取搜索图片的参数
    os_ = img_data.get('os')
    cs_ = img_data.get('cs')
    if os_ and cs_:
        # 获取搜索图片的信息
        img_search_url = f'http://image.baidu.com/search/detail?ct=503316480&z=0&ipn=d&word=%E9%A3%8E%E6%99%AF&step_word=&hs=0&pn=1&spn=0&di=195030&pi=0&rn=1&tn=baiduimagedetail&is=0%2C0&istype=0&ie=utf-8&oe=utf-8&in=&cl=2&lm=-1&st=-1&cs={cs_}&os={os_}'
        img_search_response = requests.get(img_search_url)
        img_search_data = img_search_response.text

        # 获取图片信息
        img_url = re.findall('''('firstSc');" src="(.*?)"''', img_search_data)[0]
        img_name = img_url.split('/')[-1]
        img_name = os.path.join('百度图片', img_name)  # 拼接出图片的地址，如 百度图片/3822951_144045377000_2.jpg

        # 保存图片
        img_response = requests.get(img_url)
        img_data = img_response.content
        fw = open(img_name, 'wb')
        fw.write(img_data)
        fw.flush()

        # 提示
        count += 1
        print(f'{img_name}保存成功，成功保存{count}张')

        # 防止百度禁ip，慢一点
        time.sleep(0.01)