2020Python爬虫学习笔记（一）

#demo1 有道词典翻译单词
import requests
if __name__=="__main__":
    url='http://fanyi.youdao.com/translate?smartresult=dict&smartresult=rule'
    headers={"User-Agent":"Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3947.100 Safari/537.36"}
    data={"i": "爬虫",
        "from": "AUTO",
        "to":" AUTO",
        "smartresult":" dict",
        "client":" fanyideskweb",
        "salt":" 16005916230854",
        "sign":" 52a079bc398239965ce16964323456af",
        "lts":" 1600591623085",
        "bv":" 656f750600466990f874a839d9f5ad23",
        "doctype":" json",
        "version":" 2.1",
        "keyfrom":" fanyi.web",
        "action":" FY_BY_REALTlME"}
    response=requests.post(url,headers=headers,data=data)
    with open('./youdao.html','w',encoding='UTF-8') as fp:
      fp.write(response.text)
print(response.text)

#########################################################################################

#demo2 爬取网易云音乐
import requests
from lxml import etree

##########################################################################################

#demo3 输入任意字符保存返回的网页结果
import requests
if __name__=="__main__":
    #在百度查询一个词时的链接 参数为word 所以后面param中键为‘word’
    #https://www.baidu.com/s?word=TypeError%3A%20get()%20takes%20from%201%20to%202%20positional%20arguments%20but%203%20were%20given&tn=site888_3_pg&lm=-1&ssl_s=1&ssl_c=ssl1_174b010a917&prec=1
    url='https://www.baidu.com/s'
    headers={"User-Agent":"Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3947.100 Safari/537.36"}
    kw=input('enter a word :')
    param={'word':kw}
    response = requests.get(url=url,params=param,headers=headers)
    #response = requests.get(url, param, headers)#报错
    filename = kw+'.html'
    with open(filename,'w',encoding='UTF-8') as fp:
        fp.write(response.text)
    print(filename,'保存成功!')

##########################################################################################
#demo4 破解百度翻译
import requests
import json
if __name__=="__main__":
    #url可以在审查元素 ->network-> headers-> Requrst URL
    #xhr json请求
    url='https://fanyi.baidu.com/sug'
    #UA伪装 User-Agent
    headers={"user-agent":"Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3947.100 Safari/537.36"}
    #post请求 headers 中有一个头 form-data 发送请求时携带的参数
    kw = input('enter a word : ')
    data={"kw":kw}
    #审查元素 点开network 查看请求头就知道是什么请求方式
    post_response  = requests.post(url=url,data=data,headers=headers)
    #json()方法 返回一个对象  text()返回字符串只有返回类型是json时才可使用  可在审查元素 network response content-type中查看
    dic_obj = post_response.json()#返回字典对象
    #持久化操作
    filename = kw+'.json'
    fp = open(filename,'w',encoding='UTF-8')
    json.dump(dic_obj,fp=fp,ensure_ascii=False)#我们拿到的是中文数据 中文不能使用ASCII编码 所以FALSE
    #这是因为json.dumps 序列化时对中文默认使用的ascii编码.想输出真正的中文需要指定ensure_ascii=False：



####################################################################################################
#demo5 豆瓣电影
import requests
import json
if __name__=="__main__":
    url='https://movie.douban.com/j/chart/top_list'
    #GET请求中  network   Query String Parameters  做请求参数
    params={"type": "20",
            "interval_id": "100:90",
            "action":"",
            "start": "20",
            "limit": "20"}
    headers={"User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3947.100 Safari/537.36"}
    response = requests.get(url=url,params=params,headers=headers)
    json_resp = response.json()
    fp = open('./movie.json','w',encoding='UTF-8')
    json.dump(json_resp,fp=fp,ensure_ascii=False)
    print('电影抓取完成')


#############################################
#demo6  抓取肯德基餐厅地址
import requests
if __name__=="__main__":
    url='http://www.kfc.com.cn/kfccda/ashx/GetStoreList.ashx?op=keyword'
    headers = {"User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3947.100 Safari/537.36"}
    kw  = input('enter a city : ')
    #POST请求中  From Data做请求参数
    params = {"cname":"",
    "pid":"",
    "keyword": kw,
    "pageIndex": "1",
    "pageSize": "10"}
    response = requests.post(url=url,params=params,headers=headers)
    with open('./resterant.html','w',encoding='UTF-8') as fp:
        fp.write(response.text)