Python-Requests爬虫实例

requests破解百度翻译

# -*- coding: utf-8 -*-
import requests
import json

if __name__ == '__main__':
    url = 'https://fanyi.baidu.com/basetrans'
    headers = {
        'User-Agent': 'Mozilla/5.0 (Linux; Android 6.0; Nexus 5 Build/MRA58N) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/89.0.4389.90 Mobile Safari/537.36',
        'Referer':'https://fanyi.baidu.com/?aldtype=16047',
        'Cookie':'BIDUPSID=1E64848A7B840FDD0E2923266C07A98A; PSTM=1616913998; BAIDUID=1E64848A7B840FDD5C099A513854FDE2:FG=1; FANYI_WORD_SWITCH=1; REALTIME_TRANS_SWITCH=1; HISTORY_SWITCH=1; SOUND_PREFER_SWITCH=1; SOUND_SPD_SWITCH=1; td_cookie=1233489163; __yjs_duid=1_9f4322f1a1a2759cc92311f6041071d81619750212245; H_PS_PSSID=33985_33969_31254_33848_33607_26350_33892; BAIDUID_BFESS=1E64848A7B840FDD5C099A513854FDE2:FG=1; delPer=0; PSINO=3; BDORZ=B490B5EBF6F3CD402E515D22BCDA1598; BCLID=7792273175421115645; BDSFRCVID=mU8OJexroG38EYQe91zlhKIRQuweG7bTDYLEOwXPsp3LGJLVJeC6EG0Pts1-dEu-EHtdogKKLgOTHULF_2uxOjjg8UtVJeC6EG0Ptf8g0M5; H_BDCLCKID_SF=tR3aQ5rtKRTffjrnhPF3Q-LvXP6-hnjy3bAOKxTt5CT-SRrdyUrC0JLWbttf5q3RymJJ2-39LPO2hpRjyxv4y4Ldj4oxJpOJ-bCL0p5aHl51fbbvbURvX--g3-7PWU5dtjTO2bc_5KnlfMQ_bf--QfbQ0hOhqP-jBRIEoCvt-5rDHJTg5DTjhPrMMhjrWMT-MTryKK8y3xTGeDTC3losyUFw0qofKx-fKHnRhlRNB-3iV-OxDUvnyxAZyxomtfQxtNRJQKDE5p5hKq5S5-OobUPUXMJ9LUvPBgcdot5yBbc8eIna5hjkbfJBQttjQn3hfIkj2CKLtCvDqTrP-trf5DCShUFsLJbJB2Q-XPoO3K8WsfTPbjua24AJyPrNQRQf5mkf3fbgylRM8P3y0bb2DUA1y4vpBtQmJeTxoUJ2-KDVeh5Gqfo15-0ebPRiWPb9QgbP2pQ7tt5W8ncFbT7l5hKpbt-q0x-jLTnhVn0MBCK0hDvPKITD-tFO5eT22-usaGIO2hcHMPoosI89QqrGbjcL2xv3BMcNL6Tf0l05KfbUoqRHXnJi0btQDPvxBf7pWDTm_q5TtUJMqIDzbMohqfLn5MOyKMniBIv9-pnGBpQrh459XP68bTkA5bjZKxtq3mkjbPbDfn028DKu-n5jHjjbjG_83H; BCLID_BFESS=7792273175421115645; BDSFRCVID_BFESS=mU8OJexroG38EYQe91zlhKIRQuweG7bTDYLEOwXPsp3LGJLVJeC6EG0Pts1-dEu-EHtdogKKLgOTHULF_2uxOjjg8UtVJeC6EG0Ptf8g0M5; H_BDCLCKID_SF_BFESS=tR3aQ5rtKRTffjrnhPF3Q-LvXP6-hnjy3bAOKxTt5CT-SRrdyUrC0JLWbttf5q3RymJJ2-39LPO2hpRjyxv4y4Ldj4oxJpOJ-bCL0p5aHl51fbbvbURvX--g3-7PWU5dtjTO2bc_5KnlfMQ_bf--QfbQ0hOhqP-jBRIEoCvt-5rDHJTg5DTjhPrMMhjrWMT-MTryKK8y3xTGeDTC3losyUFw0qofKx-fKHnRhlRNB-3iV-OxDUvnyxAZyxomtfQxtNRJQKDE5p5hKq5S5-OobUPUXMJ9LUvPBgcdot5yBbc8eIna5hjkbfJBQttjQn3hfIkj2CKLtCvDqTrP-trf5DCShUFsLJbJB2Q-XPoO3K8WsfTPbjua24AJyPrNQRQf5mkf3fbgylRM8P3y0bb2DUA1y4vpBtQmJeTxoUJ2-KDVeh5Gqfo15-0ebPRiWPb9QgbP2pQ7tt5W8ncFbT7l5hKpbt-q0x-jLTnhVn0MBCK0hDvPKITD-tFO5eT22-usaGIO2hcHMPoosI89QqrGbjcL2xv3BMcNL6Tf0l05KfbUoqRHXnJi0btQDPvxBf7pWDTm_q5TtUJMqIDzbMohqfLn5MOyKMniBIv9-pnGBpQrh459XP68bTkA5bjZKxtq3mkjbPbDfn028DKu-n5jHjjbjG_83H; Hm_lvt_afd111fa62852d1f37001d1f980b6800=1620813569,1620819708; Hm_lvt_64ecd82404c51e03dc91cb9e8c025574=1620813284,1620813294,1620819708,1620819712; __yjs_st=2_M2I0MjI3ZTEwM2UyZjAwZDJhYjljMDdhNGFiNDhkZTgwNjY0Y2U0NGYzMjBiZWY1NzJkYWYxMzA3ZWIzNWM1ZTE5ZDhhYzFiNGE2MzllZjBlMjMyMzEyM2UyNjA1ZDRkZjI5ZjI5N2ZjNzVlOTIyMWIzNDNiMmMxZWEzYTA5Y2M4NDBiNmRhZjRjMjZkNDJiODNlNTlmN2E5ZjVkNmYwZGEyZTliYWNiZDk4ZDhkYWMzZDYwYTY0ZjE1MjkxYTMzN2I2MjhhODE1M2UxNDBlZDQzYTIwOWIwNjczY2U3OTA0NWU3YmE0ZWQ1MGU3YzNhYzYxMmU1ZDAxNDhkMWU1NV83XzI4N2NlODFh; Hm_lpvt_afd111fa62852d1f37001d1f980b6800=1620819723; Hm_lpvt_64ecd82404c51e03dc91cb9e8c025574=1620819723; ab_sr=1.0.0_ZmE3YWU3ZTk4M2E2MTM2OGQ5Y2QwZWM3Njg0NWFkYTIzYTM2MjBmNDQzYjgzYjVhMGFmMTliNzU5ZGRmOGIxZDgzYzdhZWIzZmQ5ZjZlY2YxODk0NTk5ZGY3N2NlMWU4'
    }
    word = input('enter a word:')
    data = {
        'query': word,
        'from': 'en',
        'to': 'zh'
    }
    response = requests.post(url=url, data=data, headers=headers)
    print(response.content.decode())
    dic_obj = response.json()
    print(dic_obj)

requests豆瓣电影排行榜

import requests
import json

if __name__ == '__main__':
    url = 'https://movie.douban.com/j/chart/top_list?type=24&interval_id=100%3A90&action=&start=0&limit=20'
    param = {
        'type': '24',
        'interval_id': '100:90',
        'action':'',
        'start': '0',
        'limit': '20'
    }
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/89.0.4389.90 Safari/537.36'
    }
    response = requests.get(url=url, params=param, headers=headers).json()
    print(response)
    with open('./douban.json','w',encoding='utf-8') as fp:
        json.dump(response,fp=fp,ensure_ascii=False)

requests肯德基地理位置

import requests

if __name__ == '__main__':
    url = 'http://www.kfc.com.cn/kfccda/ashx/GetStoreList.ashx?op=keyword'
    city = input('输入查询地址：')
    param = {
        'cname':'',
        'pid':'',
        'keyword': city,
        'pageIndex': '1',
        'pageSize': '10'
    }
    header = {
        'User-Agent':'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/89.0.4389.90 Safari/537.36'
    }
    response = requests.post(url, params=param, headers=header).text
    print(response)

requests许可证信息

import requests

if __name__ == '__main__':
    url = 'http://scxk.nmpa.gov.cn:81/xk/itownet/portalAction.do?method=getXkzsList'
    param ={
        'on': 'true',
        'page': '1',
        'pageSize': '15',
        'productName':'',
        'conditionType': '1',
        'applyname':'',
        'applysn':''
    }
    header = {
        'User-Agent':'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/89.0.4389.90 Safari/537.36'
    }
    response = requests.post(url, params=param, headers=header).json()
    print(response)
    lis_ID = response['list']
    url2 = 'http://scxk.nmpa.gov.cn:81/xk/itownet/portalAction.do?method=getXkzsById'
    for item in lis_ID:
        id = item['ID']
        param2 = {
            'id': id
        }
        header2 ={
            'User-Agent':'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/89.0.4389.90 Safari/537.36'
        }
        response2 = requests.post(url2, params=param2, headers=header2).json()
        print(response2['epsName'])