什么是json?
JSON(JavaScript Object Notation) 是一种轻量级的数据交换格式,它使得人们很容易的进行阅读和编写。同时也方便了机器进行解析和生成。适用于进行数据交互的场景,比如网站前台与后台之间的数据交互。
json有四个方法供我们进行数据转换:
mydict = {'name': 'xiaoming', 'age': 18}
#json.dumps 实现python类型转化为json字符串
json_str = json.dumps(mydict)
#json.loads 实现json字符串转化为python的数据类型
my_dict = json.loads(json_str)
#json.dump 实现把python类型写入类文件对象
with open("temp.txt","w") as f:
json.dump(mydict,f,ensure_ascii=False,indent=2)
# json.load 实现类文件对象中的json字符串转化为python类型
with open("temp.txt","r") as f:
my_dict = json.load(f)
json模块的作用?
Json在数据交换中起到了一个载体的作用,承载相互传递的数据
什么是正则表达式?
用事先定义好的一些特定字符、及这些特定字符的组合,组成一个规则字符串,这个规则字符串用来表达对字符串的一种过滤逻辑。
正则表达式的常见语法
练习
1.爬取百度翻译数据,可以中英文相互翻译
# coding=utf-8
import requests
import json
import sys
class Fanyi:
def __init__(self,query_string):
self.url = "http://fanyi.baidu.com/basetrans"
self.query_string = query_string
self.headers = {"User-Agent": "Mozilla/5.0 (iPhone; CPU iPhone OS 11_0 like Mac OS X) AppleWebKit/604.1.38 (KHTML, like Gecko) Version/11.0 Mobile/15A372 Safari/604.1"}
self.langdetect_url = "http://fanyi.baidu.com/langdetect"
def get_post_data(self):#1.url,post_data
#1.url
data = {"query": self.query_string}
#2.发送请求,获取响应
json_str = self.parse_url(self.langdetect_url,data)
#3.提取数据
lan = json.loads(json_str)["lan"]
to = "en" if lan=="zh" else "zh"
post_data = {"query": self.query_string,
"from": lan,
"to": to}
return post_data
def parse_url(self,url,data):#发送请求,获取响应
resposne = requests.post(url,data=data,headers=self.headers)
return resposne.content.decode()
def get_ret(self,json_str):#3.提取数据
temp_dict = json.loads(json_str)
ret = temp_dict["trans"][0]["dst"]
print("{} :{}".format(self.query_string,ret))
def run(self):#实现主要逻辑
#1.url,post_data
post_data= self.get_post_data()
#2.发送请求,获取响应
json_str = self.parse_url(self.url,post_data)
#3.提取数据
self.get_ret(json_str)
if __name__ == '__main__':
# query_string = sys.argv[1]
query_string = "hello"
fanyi = Fanyi(query_string)
fanyi.run()
2.爬取豆瓣电视剧上英剧和美剧两个分类的电视数据,地址:https://m.douban.com/tv/
# coding=utf-8
import requests
import json
class Douban:
def __init__(self):
self.url_temp_list = [
{
"url_temp": "https://m.douban.com/rexxar/api/v2/subject_collection/filter_tv_american_hot/items?start={}&count=18&loc_id=108288",
"referer": "https://m.douban.com/tv/american"
},
{
"url_temp": "https://m.douban.com/rexxar/api/v2/subject_collection/filter_tv_english_hot/items?start={}&count=18&loc_id=108288",
"referer": "https://m.douban.com/tv/british"
},
]
self.headers = {
"User-Agent": "Mozilla/5.0 (Linux; Android 5.0; SM-G900P Build/LRX21T) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/66.0.3359.117 Mobile Safari/537.36"
}
# 获取响应的数据
def parse_url(self, url):
print(url)
resp = requests.get(url, headers = self.headers)
json_str = resp.content.decode()
return json_str
# 提取获取的数据
def get_content_list(self,json_str):
temp_dict = json.loads(json_str)
return temp_dict["subject_collection_items"]
# 保存搜索到的数据
def save_content_list(self,content_list):
with open("douban.txt","a",encoding="utf-8") as f:
for content in content_list:
f.write(json.dumps(content,ensure_ascii=False))
f.write("\n")
print("保存成功")
def run(self):
for url_temp in self.url_temp_list:
self.headers.update({"referer":url_temp["referer"]})
num = 0
while True:
# 获取url地址
next_url = url_temp["url_temp"].format(num)
# 发送请求,获取响应的数据
json_str = self.parse_url(next_url)
# 提取数据
content_list = self.get_content_list(json_str)
# 保存搜索到的数据
self.save_content_list(content_list)
num+=18
if len(content_list)<18:
break
if __name__ == '__main__':
douban = Douban()
douban.run()
3.爬取果壳上的数据源
# coding=utf-8
import requests
import re
import json
class Gouke:
def __init__(self):
self.url_temp = "https://www.guokr.com/ask/highlight/?page={}"
self.headers = {
"User-Agent": "Mozilla/5.0 (Linux; Android 5.0; SM-G900P Build/LRX21T) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/66.0.3359.117 Mobile Safari/537.36"
}
def get_url_list(self):
return [self.url_temp.format(i) for i in range(1,21)]
def parse_url(self, url):
print(url)
resp = requests.get(url, headers=self.headers)
html_str=resp.content.decode()
return html_str
def get_content_list(self,html_str):
content_list = re.findall(r"<h2><a target=\"_blank\" href=\"(.*?)\">(.*?)</a></h2>",html_str,re.S)
return content_list
def save_content_list(self,content_list): #提取数据,保存
with open("guoke.txt", "a", encoding="utf-8") as f:
for content in content_list:
f.write(json.dumps(content, ensure_ascii=False))
f.write("\n")
print("保存成功")
def run(self):#实现主要逻辑
#1. url_list
url_list = self.get_url_list()
#2. 遍历,发送请求,获取响应
for url in url_list:
html_str = self.parse_url(url)
#3. 提取数据
content_list = self.get_content_list(html_str)
#4.保存
self.save_content_list(content_list)
if __name__ == '__main__':
guoke = Gouke()
guoke.run()