import jieba
def cut_info():
  with open("comment.txt","r",encoding="utf-8") as f:
    text=f.read()
    cut_text=" ".join(jieba.cut(text))
    with open("cut_text.txt","w",encoding="utf-8") as f:
      f.write(cut_text)
cut_info()

conn=pymysql.connect(
    host="127.0.0.1",
    port=3306,
    user="root",
    password="123456",
    database="douban"
)

cursor=conn.cursor() #创建游标对象

import requests


url="图片链接.jpg"
res=requests.get(url,headers)
res.enconding="utf-8"
html=res.content  #将图片转换为二进制字节流
with open("data.jpg","wb") as f:
    f.write(html)

import requests
from lxml import etree
from user_headers import L
import random
import os


class Cunjin:
    def __init__(self):
        self.url="http://www.gdcjxy.com/index.html"
        self.headers={"User-Agent":random.choice(L)}

    def get_html(self,url):  #获取网页源代码并将源代码转换成xpath的函数
        res=requests.get(url,headers=self.headers)
        res.encoding="utf-8"
        html=res.text
        parse_html=etree.HTML(html) #将源代码转换为xpath对象
        return parse_html

    def get_t_link(self): #获取帖子中的站内链接的函数并拼接成完整链接
        self.files="./寸金学院"
        if not os.path.exists(self.files): #检测当前路径是否存在同名文件夹
            os.mkdir(self.files)
        parse_html=self.get_html(self.url) #对官网主页发起请求
        t_url=parse_html.xpath('//a[@class="p"]/@href')
        for link in t_url:
            url="http://www.gdcjxy.com"+link
            self.get_pic_url(url) #调用获取图片链接的函数


    def get_pic_url(self,url): #获取所有图片链接的函数
        parse_html=self.get_html(url)
        pic_url=parse_html.xpath('//span[@style="font-size:18px;"]/img/@src')
        for link in pic_url:
            pic_link="http://www.gdcjxy.com"+link
            filename=self.files+"//"+pic_link[-15:] #以图片链接的后15位作为图片的名称
            self.save_pic(pic_link,filename) #调用保存图片的函数

    def save_pic(self,pic_link,filename): #将图片下载到本地的函数
        res=requests.get(pic_link,headers=self.headers)
        res.encoding="utf-8"
        html=res.content
        with open(filename,"wb") as f:
            f.write(html)
            print(filename,"下载成功！")


cunjin=Cunjin()
cunjin.get_t_link()

import requests


url="https://www.baidu.com/"  #确定抓取网页的url
res=requests.get(url)  # 对网页发起请求并获取响应信息
res.encoding="utf-8"
html=res.text #解析得到的相应内容
print(html)

import requests


url="https://www.baidu.com/"  #确定抓取网页的url
headers={"User-Agent":"Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.142 Safari/537.36"}
res=requests.get(url,headers=headers)  # 对网页发起请求并获取响应信息
res.encoding="utf-8"
html=res.text #解析得到的相应内容
print(html)

import requests

url="https://www.baidu.com/s?"
headers={"User-Agent":"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/534.50 (KHTML, like Gecko) Version/5.1 Safari/534.50",
         "Cookie":"BIDUPSID=20BA20A6474681053EA56436BC4B3D97; PSTM=1574518658; BAIDUID=9276E50B9B762C87B246AFFF86AFE4CB:FG=1; BD_UPN=12314753; ispeed_lsm=2; BDORZ=B490B5EBF6F3CD402E515D22BCDA1598; COOKIE_SESSION=25_0_9_6_9_8_0_0_9_5_3_0_0_0_0_0_1575166622_0_1575337152%7C9%230_0_1575337152%7C1; H_PS_645EC=326b1bFfVwAZMn%2BEr2lUzz5jDYz09GAGHFBdUD0mYZboAS5tNtdv1A7yck4; delPer=0; BDUSS=FpvfnhINXpMeldCMU5NRDQ0STdRNi1QS2RLaDFKSTZHcnR2aEJLZmVxZWpUUTFlRUFBQUFBJCQAAAAAAAAAAAEAAAA2JBrPZmx50sHA-9ChuOe45wAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAKPA5V2jwOVdb; BD_HOME=1; H_PS_PSSID=1438_21105_30210_20698_22159"}
params={
    "wd":"篮球"
}
res=requests.get(url,headers=headers,params=params)
res.encoding="utf-8"
html=res.text
print(res.url) #返回请求的真实url地址
print(html)