全网最全系统学习爬虫教程，用爬虫进行数据分析（bs4,xpath,正则表达式)

大大源码 • • 其他

1.bs4解析基础

2.bs4案例

3.xpath解析基础

4.xpath解析案例-4k图片解析爬取

5.xpath解析案例-58二手房

6.xpath解析案例-爬取站长素材中免费简历模板

7.xpath解析案例-全国城市名称爬取

8.正则解析

9.正则解析-分页爬取

10.爬取图片

在这里插入图片描述

1.bs4解析基础

from bs4 import BeautifulSoup

fp = open('第三章 数据分析/text.html','r',encoding='utf-8')
soup = BeautifulSoup(fp,'lxml')
#print(soup)
#print(soup.a)
#print(soup.div)
#print(soup.find('div'))
#print(soup.find('div',class_="song"))
#print(soup.find_all('a'))
#print(soup.select('.tang'))
#print(soup.select('.tang > ul > li >a')[0].text)
#print(soup.find('div',class_="song").text)
#print(soup.find('div',class_="song").string)
print(soup.select('.tang > ul > li >a')[0]['href'])

2.bs4案例

from bs4 import BeautifulSoup
import requests

headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/86.0.4240.193 Safari/537.36'
}
url = "http://sanguo.5000yan.com/"

page_text = requests.get(url ,headers = headers).content
#print(page_text)

soup = BeautifulSoup(page_text,'lxml')

li_list = soup.select('.list > ul > li')

fp = open('./sanguo.txt','w',encoding='utf-8')
for li in li_list:
    title = li.a.string
    #print(title)
    detail_url = 'http://sanguo.5000yan.com/'+li.a['href']
    print(detail_url)
    detail_page_text = requests.get(detail_url,headers = headers).content
    detail_soup = BeautifulSoup(detail_page_text,'lxml')
    div_tag = detail_soup.find('div',class_="grap")
    content = div_tag.text
    fp.write(title+":"+content+'\n')
    print(title,'爬取成功！！！')

3.xpath解析基础

from lxml import etree

tree = etree.parse('第三章 数据分析/text.html')
# r = tree.xpath('/html/head/title')
# print(r)
# r = tree.xpath('/html/body/div')
# print(r)
# r = tree.xpath('/html//div')
# print(r)
# r = tree.xpath('//div')
# print(r)
# r = tree.xpath('//div[@class="song"]')
# print(r)
# r = tree.xpath('//div[@class="song"]/P[3]')
# print(r)
# r = tree.xpath('//div[@class="tang"]//li[5]/a/text()')
# print(r)
# r = tree.xpath('//li[7]/i/text()')
# print(r)
# r = tree.xpath('//li[7]//text()')
# print(r)
# r = tree.xpath('//div[@class="tang"]//text()')
# print(r)
# r = tree.xpath('//div[@class="song"]/img/@src')
# print(r)

4.xpath解析案例-4k图片解析爬取

import requests
from lxml import etree
import os

headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/86.0.4240.193 Safari/537.36'
}

url = 'http://pic.netbian.com/4kmeinv/'
response = requests.get(url,headers = headers)
#response.encoding=response.apparent_encoding
#response.encoding = 'utf-8'
page_text = response.text
tree = etree.HTML(page_text)

li_list = tree.xpath('//div[@class="slist"]/ul/li')

# if not os.path.exists('./picLibs'):
#     os.mkdir('./picLibs')
for li in li_list:
    img_src = 'http://pic.netbian.com/'+li.xpath('./a/img/@src')[0]
    img_name = li.xpath('./a/img/@alt')[0]+'.jpg'
    img_name = img_name.encode('iso-8859-1').decode('gbk')
    # print(img_name,img_src)
    # print(type(img_name))

    img_data = requests.get(url = img_src,headers = headers).content
    img_path ='picLibs/'+img_name
    #print(img_path)

    with open(img_path,'wb') as fp:

        fp.write(img_data)
        print(img_name,"下载成功")

5.xpath解析案例-58二手房

import requests
from lxml import etree

url = 'https://bj.58.com/ershoufang/p2/'
headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/86.0.4240.193 Safari/537.36'
}

page_text = requests.get(url=url,headers = headers).text

tree = etree.HTML(page_text)

li_list = tree.xpath('//section[@class="list-left"]/section[2]/div')

fp = open('58.txt','w',encoding='utf-8')
for li in li_list:
    title = li.xpath('./a/div[2]/div/div/h3/text()')[0]
    print(title)
    fp.write(title+'\n')

6.xpath解析案例-爬取站长素材中免费简历模板

import requests
from lxml import etree
import os

headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/86.0.4240.193 Safari/537.36'
}

url = 'https://www.aqistudy.cn/historydata/'
page_text = requests.get(url,headers = headers).text

7.xpath解析案例-全国城市名称爬取

import requests
from lxml import etree
import os

headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/86.0.4240.193 Safari/537.36'
}

url = 'https://www.aqistudy.cn/historydata/'
page_text = requests.get(url,headers = headers).text

tree = etree.HTML(page_text)
# holt_li_list = tree.xpath('//div[@class="bottom"]/ul/li')

# all_city_name = []
# for li in holt_li_list:
#     host_city_name = li.xpath('./a/text()')[0]
#     all_city_name.append(host_city_name)

# city_name_list = tree.xpath('//div[@class="bottom"]/ul/div[2]/li')
# for li in city_name_list:
#     city_name = li.xpath('./a/text()')[0]
#     all_city_name.append(city_name)

# print(all_city_name,len(all_city_name))

#holt_li_list = tree.xpath('//div[@class="bottom"]/ul//li')
holt_li_list = tree.xpath('//div[@class="bottom"]/ul/li | //div[@class="bottom"]/ul/div[2]/li')
all_city_name = []
for li in holt_li_list:
    host_city_name = li.xpath('./a/text()')[0]
    all_city_name.append(host_city_name)
    print(all_city_name,len(all_city_name))

8.正则解析

import requests
import re
import os

if not os.path.exists('./qiutuLibs'):
    os.mkdir('./qiutuLibs')

url = 'https://www.qiushibaike.com/imgrank/'
headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/89.0.4385.0 Safari/537.36'
}

page_text = requests.get(url,headers = headers).text


ex = '<div class="thumb">.*?<img src="(.*?)" alt.*?</div>'
img_src_list = re.findall(ex,page_text,re.S)
print(img_src_list)
for src in img_src_list:
    src = 'https:' + src

    img_data = requests.get(url = src,headers = headers).content
    img_name = src.split('/')[-1]
    imgPath = './qiutuLibs/'+img_name
    with open(imgPath,'wb') as fp:
        fp.write(img_data)
        print(img_name,"下载完成！！！！！")

9.正则解析-分页爬取

import requests
import re
import os

if not os.path.exists('./qiutuLibs'):
    os.mkdir('./qiutuLibs')

headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/89.0.4385.0 Safari/537.36'
}

url = 'https://www.qiushibaike.com/imgrank/page/%d/'

for pageNum in range(1,3):
    new_url = format(url%pageNum)

    page_text = requests.get(new_url,headers = headers).text


    ex = '<div class="thumb">.*?<img src="(.*?)" alt.*?</div>'
    img_src_list = re.findall(ex,page_text,re.S)
    print(img_src_list)
    for src in img_src_list:
        src = 'https:' + src

        img_data = requests.get(url = src,headers = headers).content
        img_name = src.split('/')[-1]
        imgPath = './qiutuLibs/'+img_name
        with open(imgPath,'wb') as fp:
            fp.write(img_data)
            print(img_name,"下载完成！！！！！")

10.爬取图片

import requests

url = 'https://pic.qiushibaike.com/system/pictures/12404/124047919/medium/R7Y2UOCDRBXF2MIQ.jpg'
img_data = requests.get(url).content

with open('qiutu.jpg','wb') as fp:
    fp.write(img_data)

关于Python技术储备

学好 Python 不论是就业还是做副业赚钱都不错，但要学会 Python 还是要有一个学习规划。最后大家分享一份全套的 Python 学习资料，给那些想学习 Python 的小伙伴们一点帮助！

一、Python所有方向的学习路线

Python所有方向的技术点做的整理，形成各个领域的知识点汇总，它的用处就在于，你可以按照上面的知识点去找对应的学习资源，保证自己学得较为全面。（文末获取！）
在这里插入图片描述
温馨提示：篇幅有限，已打包文件夹，获取方式在“文末”！！！

二、Python必备开发工具

在这里插入图片描述

三、精品Python学习书籍

当我学到一定基础，有自己的理解能力的时候，会去阅读一些前辈整理的书籍或者手写的笔记资料，这些笔记详细记载了他们对一些技术点的理解，这些理解是比较独到，可以学到不一样的思路。
在这里插入图片描述

四、Python视频合集

观看零基础学习视频，看视频学习是最快捷也是最有效果的方式，跟着视频中老师的思路，从基础到深入，还是很容易入门的。
在这里插入图片描述
在这里插入图片描述

五、实战案例

光学理论是没用的，要学会跟着一起敲，要动手实操，才能将自己的所学运用到实际当中去，这时候可以搞点实战案例来学习。
在这里插入图片描述

六、Python练习题

检查学习结果。
在这里插入图片描述

七、面试资料

我们学习Python必然是为了找到高薪的工作，下面这些面试题是来自阿里、腾讯、字节等一线互联网大厂最新的面试资料，并且有阿里大佬给出了权威的解答，刷完这一套面试资料相信大家都能找到满意的工作。
在这里插入图片描述
在这里插入图片描述

这份完整版的Python全套学习资料已经上传CSDN，朋友们如果需要可以微信扫描下方CSDN官方认证二维码免费领取【保证100%免费】

版权声明：本文为m0_59164304原创文章，遵循 CC 4.0 BY-SA 版权协议，转载请附上原文出处链接和本声明。
THE END
< <上一篇
下一篇>>