python 图片爬取

百度：

import requests
from lxml import etree

Search_term = input('请输入需要搜索的关键词')
page = input('请输入要爬取多少页（一页30章图片）：')
page = int(page) + 1
header = {
    'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 11_1_0) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/87.0.4280.88 Safari/537.36'
}
n = 0
pn = 1
# pn是从第几张图片获取 百度图片下滑时默认一次性显示30张
for m in range(1, page):
    url = 'https://image.baidu.com/search/acjson?'

    param = {
        'tn': 'resultjson_com',
        'logid': '8846269338939606587',
        'ipn': 'rj',
        'ct': '201326592',
        'is': '',
        'fp': 'result',
        'queryWord': Search_term,
        'cl': '2',
        'lm': '-1',
        'ie': 'utf-8',
        'oe': 'utf-8',
        'adpicid': '',
        'st': '-1',
        'z': '',
        'ic': '',
        'hd': '',
        'latest': '',
        'copyright': '',
        'word': Search_term,
        's': '',
        'se': '',
        'tab': '',
        'width': '',
        'height': '',
        'face': '0',
        'istype': '2',
        'qc': '',
        'nc': '1',
        'fr': '',
        'expermode': '',
        'force': '',
        'cg': 'girl',
        'pn': pn,  # 从第几张图片开始
        'rn': '30',
        'gsm': '1e',
    }
    page_text = requests.get(url=url, headers=header, params=param)
    page_text.encoding = 'utf-8'
    page_text = page_text.json()
    info_list = page_text['data']
    del info_list[-1]
    img_path_list = []
    for i in info_list:
        img_path_list.append(i['thumbURL'])

    for img_path in img_path_list:
        img_data = requests.get(url=img_path, headers=header).content
        img_path = './' + str(n) + '.jpg'
        with open(img_path, 'wb') as fp:
            fp.write(img_data)
        n = n + 1

    pn += 29


必应：

import requests,lxml
from lxml import etree

header = {
    'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 11_1_0) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/87.0.4280.88 Safari/537.36'
}

param = {'q': '狗',
 'first': '36', #开始页码
 'count': '35',
 'cw': '1177',
 'ch': '500',
 'relp': '35',
 'tsc': 'ImageHoverTitle',
 'datsrc': 'I',
 'layout': 'RowBased_Landscape',
 'mmasync': '1',
 'dgState': 'x * 288_y * 960_h * 187_c * 1_i * 106_r * 20', #
  'IG': 'A26F88CB79FA45C2994C9ED8A20099E4',
'SFX': '4',
'iid': 'images.5559'}
url = 'https://cn.bing.com/images/search?q=%e7%8c%ab&form=HDRSC2&first=1&tsc=ImageHoverTitle'

html = requests.get(url=url,headers=header,params=param)
html.encoding = 'utf-8'
page_text = html.text
# print(page_text)
page = etree.HTML(page_text)
page_texts = page.xpath('//*[@id="mmComponent_images_5559_4_1"]/ul/li/div/div[1]/a/div/img//@src')#
print(len(page_texts))
for url in page_texts:
 print(url)


360：

搜狗：