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：
(2条消息) 基于Python爬取Bing图片_钱彬 (Qian Bin)的博客-CSDN博客_爬取bing图片

import requests
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'
}
word = '狗'
param = {
    'q': word,
    'first': '', #开始页面
    'count': '35', #显示数量
    'cw': '1177',
    'ch': '500',
    'relp': '35',
    'tsc': 'ImageHoverTitle',
    'datsrc': 'I',
    'layout': 'RowBased_Landscape',
    'mmasync': '1',
    'dgState': 'x*292_y*1367_h*189_c*1_i*36_r*8',
    'IG': 'AE35C967F6624BE1845980CFA2CA81CD',
    'SFX': '2',
    'iid': 'images.5559',
}



url = 'https://cn.bing.com/images/async?'
html = requests.get(url=url,headers=header,params=param)
html.encoding = 'utf-8'
print(html.text)
data = etree.HTML(html.text)
contents = data.xpath('//@src')
print(contents)
print(len(contents))

360：

import requests

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'
}
word = '猫'
param = {
    'callback': '',
    'q': word, #搜索词
    'qtag': '',
    'pd': '1',
    'pn': '60', #采集图片数量
    'correct': word, #搜索词
    'adstar': '0',
    'tab': 'all',
    'sid': 'cb203d75cf822734afc85fb1ee85e2a6',
    'ras': '0',
    'cn': '0',
    'gn': '0',
    'kn': '0',
    'crn': '0',
    'bxn': '0',
    'cuben': '0',
    'pornn': '0',
    'manun': '3',
    'ie':'utf-8',
    'src': 'hao_360so',
    'sn': '60',
    'ps': '63',
    'pc': '63',
    '_': '1658834743371'
}



url = 'https://image.so.com/j?'
html = requests.get(url=url,headers=header,params=param)
html.encoding = 'utf-8'
page_text = html.json()
print(page_text)

pages = page_text['list']
print(len(pages))
for i in pages:
    print(i['img'])
    print()

搜狗：

import requests

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'
}
word = '狗'
param = {
    'mode': '1',
    'start': '0', #开始页数
    'xml_len': '480', #一页显示数量，最多100章
    'query': word,
}



url = 'http://pic.sogou.com/napi/pc/searchList?'
html = requests.get(url=url,headers=header,params=param)
html.encoding = 'utf-8'
# print(html.text)
page_text = html.json()
print(page_text)
#
pages = page_text['data']
pages = pages['items']
for i in pages:
    print(i['picUrl'])
    print()
print(len(pages))