python爬虫学习06

爬取图片完整代码

import requests
import time


class Image(object):
    def __init__(self):
        self.url = 'https://image.baidu.com/search/acjson?'
        self.headers = {
            'Cookie':'BDqhfp=%E5%A3%81%E7%BA%B8%26%2600-10-1undefined%26%261663%26%263; BIDUPSID=BF6984E13024022156DD9BB4E801D3FA; PSTM=1571234378; BAIDUID=6A0DED027EA35E8E9B62F7F64263095B:FG=1; __yjs_duid=1_4c4f06ee51957e319cd6257ed40bfe551617974362291; BAIDUID_BFESS=6A0DED027EA35E8E9B62F7F64263095B:FG=1; BAIDU_WISE_UID=wapp_1622969802402_578; BDORZ=B490B5EBF6F3CD402E515D22BCDA1598; BDUSS=H5wLWQ4Y1BhTWZHdHNMTmdRTm1rZVI1fmF4R0xXR2t1STdvVkdhUTVLYWdRTzVnRVFBQUFBJCQAAAAAAAAAAAEAAABE01VzAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAKCzxmCgs8ZgU; BDUSS_BFESS=H5wLWQ4Y1BhTWZHdHNMTmdRTm1rZVI1fmF4R0xXR2t1STdvVkdhUTVLYWdRTzVnRVFBQUFBJCQAAAAAAAAAAAEAAABE01VzAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAKCzxmCgs8ZgU; indexPageSugList=%5B%22%E7%8C%AB%22%2C%22%E6%9C%BA%E7%A5%A8%E9%A2%84%E8%AE%A2%22%5D; H_PS_PSSID=34099_34042_31660_34004_33607; delPer=0; PSINO=2; BA_HECTOR=2l2la0ak002l018lid1gcgcgf0r; BDRCVFR[X_XKQks0S63]=mk3SLVN4HKm; userFrom=www.baidu.com; firstShowTip=1; BDRCVFR[dG2JNJb_ajR]=mk3SLVN4HKm; ab_sr=1.0.1_OTdiNzE1YzRmODI5YjFiYTczOWE5YzQ3ZWQ0MjE3YTlmODViNjI5NjgxZTI3YjRiYTNlZGVkMTM1NDZkNTM0YmMwZmRlZDQ5OTE5Njk1MzI4YTA1ZDRiNTNjNzZkNWI4YTcxMzA5ODhiMGIxMzc4NGI1NjJlZDI3YzM5MzBiNjJiMDJjZjVlMGEwM2Y4NjVlMzg0Y2UzZDk0OWU3NDMwMTQ0ZGFjMTVkNTNmYjlhOTRlMmI0Y2Q1ZTg1MDgyODZh; BDRCVFR[-pGxjrCMryR]=mk3SLVN4HKm'
            ,'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/90.0.4430.93 Safari/537.36'
        }
        self.params = {

            'tn': 'resultjson_com',
            'logid': '11346612270981214165',
            'ipn': 'rj',
            'ct': '201326592',
            'is': '',
            'fp': 'result',
            'queryWord': '壁纸',
            'cl': '2',
            'lm': '-1',
            'ie': 'utf-8',
            'oe': 'utf-8',
            'adpicid': '',
            'st': '-1',
            'z': '',
            'ic': '0',
            'hd': '',
            'latest': '',
            'copyright': '',
            'word': '壁纸',
            's': '',
            'se': '',
            'tab': '',
            'width': '',
            'height': '',
            'face': '0',
            'istype': '2',
            'qc': '',
            'nc': '1',
            'fr': '',
            'expermode': '',
            'force': '',
            'pn': '',
            'rn': '30',
            'gsm': '',
            'time': ''
        }
        self.image_list = []

    def get_image(self, num):
        for i in range(0, num):
            self.params['time'] = int(time.time() * 1000)
            self.params['pn'] = i * 30
            response = requests.get(url=self.url, headers=self.headers, params=self.params)
            for j in range(0, len(response.json()['data']) - 1):
                self.image_list.append(response.json()['data'][j]['thumbURL'])

    def save_image(self):
        n = 1
        for i in self.image_list:
            image = requests.get(url=i)
            with open('./图片/{}.jpg'.format(n), 'wb') as f:
                f.write(image.content)
            n += 1


if __name__ == '__main__':
    image = Image()
    image.get_image(2)
    image.save_image()

以下路径图：
a —b f
b —c d
d —r

对于如下代码

        with open(file_name, 'w', encoding='utf-8') as w:
            w.write(s_text)

如果file_name直接保存在C文件夹

1. 保存到a文件下：…/
2. 保存到f文件下：…/f/
3. 保存到d文件下：./d/r/