一、什么是爬虫？
它是指向网站发起请求，获取资源后分析并提取有用数据的程序；
爬虫的步骤：
1、发起请求
使用http库向目标站点发起请求，即发送一个Request
Request包含：请求头、请求体等
2、获取响应内容
如果服务器能正常响应，则会得到一个Response
Response包含：html，json，图片，视频等
3、解析内容
解析html数据：正则表达式（RE模块），第三方解析库如Beautifulsoup，pyquery等
解析json数据：json模块
解析二进制数据：以wb的方式写入文件
4、保存数据
数据库（MySQL，Mongdb、Redis）文件
二、本次选择爬虫的数据来源于链家，因为本人打算搬家，想观察一下近期的链家租房数据情况，所以就直接爬取了链家数据，相关的代码如下：
from bs4 import BeautifulSoup as bs
from requests.exceptions import RequestException
import requests
import re
from DBUtils import DBUtils
def main(response): #web页面数据提取与入库操作
html = bs(response.text, 'lxml')
for data in html.find_all(name='div',attrs={"class":"content__list--item--main"}):
try:
print(data)
Community_name = data.find(name="a", target="_blank").get_text(strip=True)
name=str(Community_name).split(" ")[0]
sizes=str(Community_name).split(" ")[1]
forward=str(Community_name).split(" ")[2]
flood = data.find(name="span",class_="hide").get_text(strip=True)
flood=str(flood).replace(" ","").replace("/","")
sqrt= re.compile("\d\d+㎡")
area=str(data.find(text=sqrt)).replace(" ","")
maintance=data.find(name="span",class_="content__list--item--time oneline").get_text(strip=True)
maintance=str(maintance)
price=data.find(name="span",class_="content__list--item-price").get_text(strip=True)
price=str(price)
print(name,sizes,forward,flood,maintance,price)
insertsql = "INSERT INTO test_log.`information`(Community_name,size,forward,area,flood,maintance,price) VALUES "('"+name+"','"+sizes+"','"+forward+"','"+area+"','"+flood+"','"+maintance+"','"+price+"');"
insert_sql(insertsql)
except:
print("have an error!!!")
def insert_sql(sql): #数据入库操作
dbconn=DBUtils("test6")
dbconn.dbExcute(sql)
def get_one_page(urls): #获取web页面数据
try:
headers = {"Host": "bj.lianjia.com",
"Connection": "keep-alive",
"Cache-Control": "max-age=0",
"Upgrade-Insecure-Requests": "1",
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/83.0.4103.61 Safari/537.36",
"Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.9",
"Sec-Fetch-Site": "none",
"Sec-Fetch-Mode": "navigate",
"Sec-Fetch-User": "?1",
"Sec-Fetch-Dest": "document",
"Accept-Encoding": "gzip, deflate, br",
"Accept-Language": "zh-CN,zh;q=0.9",
"Cookie": "lianjia_uuid=fa1c2e0b-792f-4a41-b48e-78531bf89136; _smt_uid=5cfdde9d.cbae95b; sensorsdata2015jssdkcross=%7B%22distinct_id%22%3A%2216b3fad98fc1d1-088a8824f73cc4-e353165-2710825-16b3fad98fd354%22%2C%22%24device_id%22%3A%2216b3fad98fc1d1-088a8824f73cc4-e353165-2710825-16b3fad98fd354%22%2C%22props%22%3A%7B%22%24latest_traffic_source_type%22%3A%22%E8%87%AA%E7%84%B6%E6%90%9C%E7%B4%A2%E6%B5%81%E9%87%8F%22%2C%22%24latest_referrer%22%3A%22https%3A%2F%2Fwww.baidu.com%2Flink%22%2C%22%24latest_referrer_host%22%3A%22www.baidu.com%22%2C%22%24latest_search_keyword%22%3A%22%E6%9C%AA%E5%8F%96%E5%88%B0%E5%80%BC%22%7D%7D; _ga=GA1.2.1891741852.1560141471; UM_distinctid=17167f490cb566-06c7739db4a69e-4313f6b-100200-17167f490cca1e; Hm_lvt_9152f8221cb6243a53c83b956842be8a=1588171341; lianjia_token=2.003c978d834648dbbc2d3aa4b226145cd7; select_city=110000; lianjia_ssid=fc20dfa1-6afb-4407-9552-2c4e7aeb73ce; CNZZDATA1253477573=1893541433-1588166864-https%253A%252F%252Fwww.baidu.com%252F%7C1591157903; CNZZDATA1254525948=1166058117-1588166331-https%253A%252F%252Fwww.baidu.com%252F%7C1591154084; CNZZDATA1255633284=1721522838-1588166351-https%253A%252F%252Fwww.baidu.com%252F%7C1591158264; CNZZDATA1255604082=135728258-1588168974-https%253A%252F%252Fwww.baidu.com%252F%7C1591153053; _jzqa=1.2934504416856578000.1560141469.1588171337.1591158227.3; _jzqc=1; _jzqckmp=1; _jzqy=1.1588171337.1591158227.1.jzqsr=baidu.-; _qzjc=1; _gid=GA1.2.1223269239.1591158230; _qzja=1.1313673973.1560141469311.1588171337488.1591158227148.1591158227148.1591158233268.0.0.0.7.3; _qzjto=2.1.0; srcid=eyJ0Ijoie1wiZGF0YVwiOlwiMThmMWQwZTY0MGNiNTliNTI5OTNlNGYxZWY0ZjRmMmM3ODVhMTU3ODNhNjMwODhlZjlhMGM2MTJlMDFiY2JiN2I4OTBkODA0M2Q0YTM0YzIyMWE0YzIwOTBkODczNTQwNzM0NTc1NjBlM2EyYTc3NmYwOWQ3OWQ4OWJjM2UwYzAwY2RjMTk3MTMwNzYwZDRkZTc2ODY0OTY0NTA5YmIxOWIzZWQyMWUzZDE3ZjhmOGJmMGNmOGYyMTMxZTI1MzIxMGI4NzhjNjYwOGUyNjc3ZTgxZjA2YzUzYzE4ZjJmODhmMTA1ZGVhOTMyZTRlOTcxNmNiNzllMWViMThmNjNkZTJiMTcyN2E0YzlkODMwZWIzNmVhZTQ4ZWExY2QwNjZmZWEzNjcxMjBmYWRmYjgxMDY1ZDlkYTFhMDZiOGIwMjI2NTg1ZGU4NTQyODBjODFmYTUyYzI0NDg5MjRlNWI0N1wiLFwia2V5X2lkXCI6XCIxXCIsXCJzaWduXCI6XCI2Yzk3M2U5M1wifSIsInIiOiJodHRwczovL2JqLmxpYW5qaWEuY29tL2RpdGllenVmYW5nL2xpNDY0NjExNzkvcnQyMDA2MDAwMDAwMDFsMSIsIm9zIjoid2ViIiwidiI6IjAuMSJ9"}
response = requests.get(url=urls, headers=headers)
main(response)
except RequestException:
return None
if __name__=="__main__":
for i in range(64): #遍历翻页
if(i==0):
urls = "https://bj.lianjia.com/ditiezufang/li46461179/rt200600000001l1/"
get_one_page(urls)
else:
urls = "https://bj.lianjia.com/ditiezufang/li46461179/rt200600000001l1/".replace("rt","pg"+str(i))
get_one_page(urls)
说明：本代码中使用了《Python之mysql实战》的那篇文章，请注意结合着一起来看。
三、以下是获取到的数据入库后的结果图
结论：爬虫是获取数据的重要方式之一，我们需要掌握多种方式去获取数据。机器学习是基于数据的学习，我们需要为机器学习做好数据的准备，大家一起加油哟~
备注：我的个人公众号已正式开通，致力于测试技术的分享，包含：大数据测试、功能测试，测试开发，API接口自动化、测试运维、UI自动化测试等，微信搜索公众号：“无量测试之道”，或扫描下方二维码：
添加关注，一起共同成长吧。