【python爬蟲】python爬取百度圖片中的圖片

話不多說，直接上代碼，一看便懂！！！！！！！！！

# coding=utf-8
"""根據搜索詞下載百度圖片"""
import re
import sys
import urllib
import requests
import random

def getPage(keyword, page, n):
    page = page * n
    keyword = urllib.parse.quote(keyword, safe='/')
    url_begin = "http://image.baidu.com/search/flip?tn=baiduimage&ie=utf-8&word="
    url = url_begin + keyword + "&pn=" + str(page) + "&gsm=" + str(hex(page)) + "&ct=&ic=0&lm=-1&width=0&height=0"
    return url


def get_onepage_urls(onepageurl):
    try:
        html = requests.get(onepageurl).text
    except Exception as e:
        print(e)
        pic_urls = []
        return pic_urls
    pic_urls = re.findall('"objURL":"(.*?)",', html, re.S)
    return pic_urls


def down_pic(pic_urls):
    """給出圖片鏈接列表, 下載所有圖片"""
    for i, pic_url in enumerate(pic_urls):
        try:
            pic = requests.get(pic_url, timeout=15)
            #string = str(i + 1) + '.jpg'
            # with open(string, 'wb') as f:
            with open('E:/bonc_projects/fire_event/dataset/pachong_new/' + (keyword+'_'+str(random.randrange(0,100000,4))+'.jpg'), 'wb') as f:
                f.write(pic.content)
                print('成功下載第%s張圖片: %s' % (str(i + 1), str(pic_url)))
        except Exception as e:
            print('下載第%s張圖片時失敗: %s' % (str(i + 1), str(pic_url)))
            print(e)
            continue


if __name__ == '__main__':
    keyword = '森林火災'  # 關鍵詞, 改爲你想輸入的詞即可, 相當於在百度圖片裏搜索一樣
    page_begin = 0
    page_number = 20
    image_number = 150
    # 百度圖片每頁顯示20張圖片，但是源碼文件中，每頁會多緩存40張，所以，請求4次的話，應該是20×4+40=120張圖片，是吻合的。
    all_pic_urls = []
    while 1:
        if page_begin > image_number:
            break
        print("第%d次請求數據" % (page_begin + 1))
        url = getPage(keyword, page_begin, page_number)
        print(url)
        onepage_urls = get_onepage_urls(url)
        page_begin += 1

        all_pic_urls.extend(onepage_urls)

    down_pic(list(set(all_pic_urls)))