【python】爬虫

# 国外路径 pip install request
# 国内源镜像路径(清华） pip install -i https://pypi.tuna.tsinghua.edu.cn/simple requests

import requests

key=input("请输入你要查询的内容:")
url = f"http://www.sogo.com/web?query={key}"
header = {
    "user-agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_13_6) AppleWebKit/537.36 (KHTML, like Gecko)"
                  "Chrome/99.0.4844.74 Safari/537.36"
}

resp = requests.get(url, headers=header) #处理了一个小小的反爬

print(resp)
print(resp.text)  # 拿到页面源代码

import requests as requests

url = "https://fanyi.baidu.com/sug"
value = input("请输入关键字：")
keyword = {
    "kw": value
}
# 发送post请求，发送的数据请求必须在字典中，通过data参数进行传递
resp = requests.post(url, data=keyword)
print(resp.json())  #将服务器返回的内容直接转换成json格式

import requests

url = "https://movie.douban.com/j/chart/top_list"

param = {
    "type": 24,
    "interval_id": "100:90",
    "action": "",
    "start": 0,
    "limit": 20
}
headers = {
    "User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_13_6) AppleWebKit/537.36 (KHTML, like Gecko)"
                  "Chrome/99.0.4844.74 Safari/537.36"
}

resp = requests.get(url=url, params=param, headers=headers)
# print(resp.request.url)   #检查url是否正确

# 把结果存到文件中
with open("豆瓣喜剧电影.txt", mode="w") as f:
    f.write(str(resp.json()))

# 关闭文件
f.close()
# 爬完一定要关闭
resp.close()