Python学习日记 2023年8月28日

import requests
from lxml import etree
import re

url = 'https://image.baidu.com/search/acjson?tn=resultjson_com&logid=8700291432374701138&ipn=rj&ct=201326592&is=&fp=result&fr=ala&word=%E8%A1%A8%E6%83%85%E5%8C%85&queryWord=%E8%A1%A8%E6%83%85%E5%8C%85&cl=2&lm=-1&ie=utf-8&oe=utf-8&adpicid=&st=&z=&ic=&hd=&latest=©right=&s=&se=&tab=&width=&height=&face=&istype=&qc=&nc=&expermode=&nojc=&isAsync=&pn=390&rn=30&gsm=186'
headers = {
    'Cookie':'winWH=%5E6_1920x963; BDIMGISLOGIN=0; BDqhfp=%E8%A1%A8%E6%83%85%E5%8C%85%26%26NaN-1undefined%26%268772%26%2614; BIDUPSID=47D1A97F74FE4D84D9C060A7E9D9623C; PSTM=1688450494; BAIDUID=64354928A148308F322D02D378FB19A4:FG=1; BAIDUID_BFESS=64354928A148308F322D02D378FB19A4:FG=1; ZFY=r0Ch4DZ4vzKkjKsCTr20yTyvBoJZR:BJjX3:AbIpxAvCs:C; BA_HECTOR=05812la52la52l80008505891ieo2c31p; PSINO=1; H_PS_PSSID=36548_39226_39223_39193_39199_39240_39233_26350_39238_39138_39224_39137_22157_39100; delPer=0; BDORZ=B490B5EBF6F3CD402E515D22BCDA1598; BDRCVFR[dG2JNJb_ajR]=mk3SLVN4HKm; BDRCVFR[-pGxjrCMryR]=mk3SLVN4HKm; BDRCVFR[tox4WRQ4-Km]=mk3SLVN4HKm; BDRCVFR[A24tJn4Wkd_]=mk3SLVN4HKm',
    'Host':'image.baidu.com',
    'Referer':'https://image.baidu.com/search/index?tn=baiduimage&ct=201326592&lm=-1&cl=2&ie=gb18030&word=%B1%ED%C7%E9%B0%FC&fr=ala&ala=1&alatpl=normal&pos=0&',
    'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/116.0.0.0 Safari/537.36'
}
data = {
    'tn': 'resultjson_com',
    'logid': '8700291432374701138',
    'ipn': 'rj',
    'ct': '201326592',
    'is': '',
    'fp': 'result',
    'fr': 'ala',
    'word': '表情包',
    'queryWord': '表情包',
    'cl': '2',
    'lm': '-1',
    'ie': 'utf-8',
    'oe': 'utf-8',
    'adpicid': '',
    'st': '',
    'z': '',
    'ic': '',
    'hd': '',
    'latest': '',
    'copyright': '',
    's': '',
    'se': '',
    'tab': '',
    'width': '',
    'height': '',
    'face': '',
    'istype': '',
    'qc': '',
    'nc': '',
    'expermode': '',
    'nojc': '',
    'isAsync': '',
    'pn': '330',
    'rn': '30',
    'gsm': '186',
      
}
resp = requests.get(url , headers=headers,data=data)

resp_json = resp.json()
resp_urls = resp_json['data']

for resp_url in resp_urls:
    try:
        fromPageTitle = resp_url['fromPageTitle']
        fromPageTitle = re.sub(r'[/\*?<>|\n_]',fromPageTitle)
        middleURL = resp_url['middleURL']
        name = re.split(r'(\w+)',middleURL)
        print(name[-10],fromPageTitle)
    except:
        continue

百度表情里面原来看起来是HTML，后来抓包发现数据竟然是json的