爬虫百度图片

'''
爬虫百度图片
'''

import re
import os
import time
import requests
from selenium import webdriver

#########################
###此段代码不需要关心啥意思###
#########################

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

#####################
###限制30张图片的代码###
####################


# # 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=美女')
# 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)

#########################################################################
###自行百度selenium的用法，使用这一套代码可以无限爬取所有图片，否则将被限制30张###

# http://npm.taobao.org/mirrors/chromedriver/
########################################################################

# pip install selenium



page_count_end = 100  # 爬取 指定数字（10）* 30 = 300张图片
word = '美女'
chrome = webdriver.Chrome()

try:

    chrome.implicitly_wait(100)
    chrome.get(
        f'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={word}')

    js_code = '''
    window.scrollTo(0, document.body.scrollHeight);
    var lenOfPage = document.body.scrollHeight;
    return lenOfPage
    '''

    # selenium控制爬取页数
    count = 0
    page_count = 0
    while page_count < page_count_end:
        try:
            page_count += 1
            chrome.execute_script(js_code)
            time.sleep(0.3)
        except:
            continue

    img_desc_search_urls = re.findall('href="(/search/detail?.*?)"', chrome.page_source, re.S)  # re.S使.可以匹配换行符

    # 获取所有图片的数据
    for img_data in img_desc_search_urls:
        try:
            # 获取搜索图片的参数
            os_ = re.findall('os=(.*?)&amp;', img_data)[0]
            cs_ = re.findall('cs=(.*?)&amp;', img_data)[0]

            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)
        except:
            continue

except Exception:
    pass

finally:
    chrome.close()


## 以上代码分两部分,前部分加注释的为数量30的百度图片:后半部分未注释的代码,可以爬虫百度图片不限制,从谷歌打开,所以默认浏览器是谷歌,另外根目录要有个chromedriver.exe文件