qq_43784519的博客

网络爬虫基本流程：① 访问站点② 定位所需的信息③ 得到并处理信息

特别注意商品价格和评价是在动态加载的，所以要找javascript价格：https://p.3.cn/prices/mgets?skuIds=J_商品id评论：https://club.jd.com/comment/productCommentSummaries.action?referenceIds=商品idimport requestsfrom lxml import etreeimport json#ctrl + F 局部查找headers = { 'User-Agent':

手机号码归属地查询import requestsimport jsonphone = input("电话号码：")url = 'http://apis.juhe.cn/mobile/get?phone={}&key=你获取的key'.format(phone)res = requests.get(url)json_data = json.loads(res.text)print("省份:",json_data['result']['province'])print("城市:",j

使用天气预报api接口import requestsimport jsoncity = input("城市：")url = 'http://v.juhe.cn/weather/index?format=2&cityname={}&key=8454d920d0801ba884a930add8a1e6de '.format(city)res = requests.get(url)json_data = json.loads(res.text)print("temperature

爬取网站图片（1.正则表达式）如果文件夹不存在，就创建文件夹。 path = "E:\\images\\" if os.path.exists(path): pass else: os.mkdir(path)import reimport requestsimport osimport urllib.requestheaders = { 'user-agent': 'Mozilla/5.0 (Windows NT 1

爬取糗事百科段子（xpath）import requestsfrom lxml import etreeheaders = { 'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/83.0.4103.116 Safari/537.36'} #加入请求头url = 'https://www.qiushibaike.com/text

爬取糗事百科的段子import requests #导入相应库import refrom bs4 import BeautifulSoupdef judge_sex(sex): if sex == "womenIcon": return '女' else: return '男'headers = { 'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/

爬取斗破苍穹小说import requests #导入相应库import reheaders = { 'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/83.0.4103.116 Safari/537.36'} #加入请求头def Get_text(url): try: res = requests.

圣诞歌曲TOP50（正则表达式）import reimport requests #导入相应库'''phone = '123-456-789'new_phone = re.sub('\D','',phone)print(new_phone) #sub()方法用于替换print(re.findall('\d',phone))'''headers = { 'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) Apple

爬取QQ音乐圣诞歌曲TOP10'''圣诞歌曲TOP10'''import requests #导入相应库from bs4 import BeautifulSoup#import timeheaders = { 'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/83.0.4103.116 Safari/537.36'}