【python数据分析】2.爬虫

最新推荐文章于 2024-07-31 14:30:10 发布

June159

最新推荐文章于 2024-07-31 14:30:10 发布

阅读量414

点赞数 1

分类专栏：笔记文章标签： python 爬虫数据分析

本文链接：https://blog.csdn.net/June159/article/details/124489167

版权

笔记专栏收录该内容

13 篇文章 0 订阅

订阅专栏

1.爬虫介绍

在这里插入图片描述

2.准备工作

在这里插入图片描述

3.构建流程

# coding:utf-8
# @Time : 22/4/29 11:20
# @Author : Justha
# @File : spider.py.py
# @Software: PyCharm

import bs4
import re
import urllib.request,urllib.error
import xlwt
import sqlite3

def main():
    print("这是main")
    baseurl = "http://movie.douban.com/top250?start="
    #1.爬取网页
    datalist = getData(baseurl)
    savapath = ".\\豆瓣电影Top250.xls"

    #3.保存数据
    savaData(savapath)
    
#爬取数据
def getData(baseurl):
    datalist = []
    return datalist

def savaData(savapath):
    print()


if __name__=="__main__":
    main()

4.urllib

getData&askURL

# coding:utf-8
# @Time : 22/5/1 15:00
# @Author : Justha
# @File : testurllib.py
# @Software: PyCharm
# 想放弃了就去给我做运动！

import urllib.request

url = "http://www.douban.com/"
headers={
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/100.0.4896.127 Safari/537.36"
}
req = urllib.request.Request(url=url,headers=headers)
response = urllib.request.urlopen(req)
print(response.read().decode("utf-8"))

5.获取数据

# coding:utf-8
# @Time : 22/4/29 11:20
# @Author : Justha
# @File : spider.py.py
# @Software: PyCharm

import bs4
import re
import urllib.request,urllib.error
import xlwt
import sqlite3

def main():
    print("这是main")
    baseurl = "http://movie.douban.com/top250?start="
    #1.爬取网页
    datalist = getData(baseurl)
    savapath = ".\\豆瓣电影Top250.xls"

    #3.保存数据
    savaData(savapath)
    
#爬取数据
def getData(baseurl):
    datalist = []
    for i in range(0,10):
        url=baseurl+str(i*25)
        print(url)
        html=askURL(url)
        datalist.append(html)
    print(datalist[9])
    return datalist


def savaData(savapath):
    print()

# 获取网页内容
def askURL(url):
    head = {
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/100.0.4896.127 Safari/537.36"
    }
    request = urllib.request.Request(url,headers=head)
    try:
        response = urllib.request.urlopen(request)
        html = response.read().decode("utf-8")
    except urllib.error.URLError as e:
        if hasattr(e,"code"):
            print(e.code)
        if hasattr(e,"reason"):
            print(e.reason)
    return html

if __name__=="__main__":
    main()

6.beautifulsoup

# coding:utf-8
# @Time : 22/5/1 16:04
# @Author : Justha
# @File : testBs4.py
# @Software: PyCharm
# 想放弃了就去给我做运动！
import re

from bs4 import BeautifulSoup

file = open("./baidu.html","rb")
html=file.read()
bs=BeautifulSoup(html,"html.parser")

# # 1.Tag 为获取到的第一个标签及其内容
# print(type(bs))
# print(type(bs.meta))    #类型为Tag
# print(bs.meta)
#
# # 2.NavigableString 标签里的内容（字符串）
# print(bs.a.string)
# print(bs.a.attrs)       #拿到标签的属性
#
# # 3.BeautifulSoup 整个文件
# # print(bs)
#
# # 4.注释（会将string里的注释去掉，拿到内容）
# print(bs.a.string)      #这里输出为新闻1，而不是<!--新闻1-->
#
# # 文档遍历
# print(bs.head.contents)
# print(bs.head.contents[1])

# 文档搜索

# # 1）find_all        findAll???
# # 字符串过滤，只会查找完全一致的内容
# a_list=bs.find_all("a",limit=3)       #标签   limit限制数量
# print(a_list)
# a_list=bs.find_all(id="head")   #id
# print(a_list)
# a_list=bs.find_all(class_=True)     #class
# print(a_list)
# a_list=bs.find_all(text=re.compile("\d"))     #标签里所有包含数字的内容
# print(a_list)


# # 2）正则表达式
# a_list2=bs.find_all(re.compile("a"))
# print(a_list2)

# 3)select
# list3=bs.select("a")    #标签
# list3=bs.select(".mnav")    #类
# list3=bs.select("#head")    #id
# list3=bs.select("a[class='bri']")    #  a.bri
# list3=bs.select("head>title")    #  head title
list3=bs.select(".mnav ~ .bri']")    #  mnav的所有同级兄弟里的br

for item in list3:
    print(item)

7.正则表达式
在这里插入图片描述

至保存sql前代码

# coding:utf-8
# @Time : 22/4/29 11:20
# @Author : Justha
# @File : spider.py.py
# @Software: PyCharm

import bs4
import re
import urllib.request,urllib.error
import xlwt
import sqlite3

def main():
    print("这是main")
    baseurl = "http://movie.douban.com/top250?start="
    #1.爬取网页
    datalist = getData(baseurl)
    # savapath = ".\\豆瓣电影Top250.xls"

    #3.保存数据
    savaData(datalist)
    
#爬取数据
def getData(baseurl):
    datalist = []
    findTitle = re.compile(r'<img.*alt="(.*?)"')
    findLink=re.compile(r'<a href="(.*?)">')
    findImgSrc=re.compile(r'<img.*src="(.*?)"',re.S)    #?代表非贪婪模式，找到一个就停止，re.S代表不管换行符
    findScore=re.compile(r'<span class="rating_num" property="v:average">(.*)</span>')
    findCommentNum=re.compile(r'<span>(\d*)人评价</span>')
    findInq=re.compile(r'<span class="inq">(.*?)</span>')
    findBd=re.compile(r'<div class="bd">.*<p class="">(.*?)</p>',re.S)

    for i in range(0,10):
        url=baseurl+str(i*25)
        print(url)
        html=askURL(url)
        soup =  bs4.BeautifulSoup(html, "html.parser")
        for item in soup.find_all('div',class_="item"):
            data = []
            item=str(item)
            # 搜索item中匹配正则表达式的内容
            title = re.findall(findTitle, item)[0]
            score = re.findall(findScore,item)[0]
            commentNum=re.findall(findCommentNum,item)[0]
            try:
                inq = re.findall(findInq, item)[0]
            except IndexError as e:
                print(e)
            bd=re.findall(findBd,item)[0]
            link = re.findall(findLink,item)[0]
            imgSrc = re.findall(findImgSrc,item)[0]
            # 输出那些内容
            print("%s  %s  %s人评价  %s\n%s\n%s\n%s"%(title,score,commentNum,inq,link,imgSrc,bd))
            # 下载图片
            # savePlace="./downloadFile/"+title+".jpg"    #图片下载保持地址
            # urllib.request.urlretrieve(imgSrc,savePlace)
            # 保存数据
            data.append(title)
            data.append(score)
            data.append(commentNum)
            data.append(inq)
            data.append(link)
            data.append(imgSrc)
            # data.append(bd)
            # print(data)
            datalist.append(data)
    # print(datalist)
    return datalist


def savaData(datalist):
    workbook = xlwt.Workbook(encoding="utf-8",style_compression=0)
    worksheet = workbook.add_sheet('sheet666',cell_overwrite_ok=True)
    title=('电影名','分数','评论人数','描述','电影链接','电影图片链接')
    for i in range(0,6):
        worksheet.write(0,i,title[i])
    for j in range(0,250):
        for k in range(0,6):
            worksheet.write(j+1,k,datalist[j][k])
    workbook.save('豆瓣Top250.xls')


# 获取网页内容
def askURL(url):
    head = {
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/100.0.4896.127 Safari/537.36"
    }
    request = urllib.request.Request(url,headers=head)
    try:
        response = urllib.request.urlopen(request)
        html = response.read().decode("utf-8")
    except urllib.error.URLError as e:
        if hasattr(e,"code"):
            print(e.code)
        if hasattr(e,"reason"):
            print(e.reason)
    return html

if __name__=="__main__":
    main()
    print("爬取完毕！")