Python爬蟲,獲取,解析,存儲詳解

1.獲取數據

import requests
def drg(url):
    try:
        head ={'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/\
       537.36 (KHTML, like Gecko) Chrome/\
       91.0.4472.164 Safari/537.36'}
        r = requests.get(url,headers=head)
        r.raise_for_status()  # 如果狀態不是200,引發HTTPError異常
        r.encoding = r.apparent_encoding
        return r.text
    except:
        return "產生異常"
url = "https://www.ip138.com/mobile.asp?mobile=13018305773&action=mobile"
print(drg(url))

2.解析數據

import requests
def login():
    try:
        # 登錄之後界面的url
        urllogin="http://www.cqooc.com/user/login?username=12608199000635&password=48C032612C2A6777D28A969307B52127E198D59AA78522943C1B283CF7B89E69&nonce=6BA36BBB1F623279&cnonce=8257070573EFE28F"
        s=requests.session()
        r=s.post(urllogin,data=Form,headers=headers)
        r.encoding = r.apparent_encoding
        r.raise_for_status()
        return s
    except Exception as error:
        print(error)
def get_html(s,url):
    try:
        r=s.get(url,headers=headers)
        r.encoding = r.apparent_encoding
        r.raise_for_status()
        return r.text
    except Exception as error:
        print(error)
if __name__=="__main__":
    # 登錄之後的界面user-agent
    headers = {
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.164 Safari/537.36",
    }
    # 跟著自己的改變
    Form = {
        "username": "12608199000635",
        "password": "48C032612C2A6777D28A969307B52127E198D59AA78522943C1B283CF7B89E69",
        "nonce": "6BA36BBB1F623279",
        "cnonce": "8257070573EFE28F"
    }
    lin=login()
    # 個人中心的網址
    url="http://www.cqooc.com/my/learn"
    html=get_html(lin,url)
    print(html)

3.數據保存為CSV格式和存入數據庫

保存為CSV

import  requests
from lxml import etree
import csv
#獲取數據
def get_html(url,time=30):
    try:
        r = requests.get(url, timeout=time)
        r.encoding = r.apparent_encoding
        r.raise_for_status()
        return r.text
    except Exception as error:
        print(error)
def parser(html): #解析函數
    doc=etree.HTML(html) #html轉換為soup對象
    out_list=[] #解析函數輸出數據的列表
    #二次查找法
    for row in  doc.xpath("//*[@class='book-img-text']//li/*[@class='book-mid-info']"):
        row_data=[
            row.xpath("h4/a/text()")[0], #書名
            row.xpath("p[@class='author']/a/text()")[0], #作者
            row.xpath("p[2]/text()")[0].strip(), #介紹
            row.xpath("p[@class='update']/span/text()")[0] #更新日期
        ]
        out_list.append(row_data) #將解析的每行數據插入到輸出列表中
    return out_list
def  save_csv(item,path): #數據存儲,將list數據寫入文件,防止亂碼
    with open(path, "a+", newline='',encoding="utf-8") as f: #創建utf8編碼文件
        csv_write = csv.writer(f) #創建寫入對象
        csv_write.writerows(item) #一次性寫入多行
if __name__=="__main__":
    for i in range(1,6):
        url="https://www.qidian.com/rank/fengyun?style=1&page={0}".format(i)
        html=get_html(url) #獲取網頁數據
        out_list=parser(html) #解析網頁,輸出列表數據
        save_csv(out_list,"d:\\book.csv") #數據存儲

存入數據庫

import pymysql
import requests
from lxml import etree
def get_html(url, time=3000):
    try:
        headers ={
            "User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/94.0.4606.61 Safari/537.36 Edg/94.0.992.31"
        }
        r = requests.get(url, timeout=time,headers=headers)
        r.encoding = r.apparent_encoding
        r.raise_for_status()
        return r.text
    except Exception as err:
        print(err)
result = []
def parse_html(html):
    html = etree.HTML(html)
    for row in html.xpath('//*[@id="content"]/div/div[1]/ul/li'):
        Naame = row.xpath("div[2]/h2/a/text()")[0].strip()#//*[@id="content"]/div/div[1]/ul[1]/div[2]/h2/a
        score = row.xpath("div[2]/p[2]/span[2]/text()")[0].strip()#//*[@id="content"]/div/div[1]/ul[1]/div[2]/p[2]/span[2]
        price = row.xpath("div[2]/p[1]/text()")[0].strip().split("/")#//*[@id="content"]/div/div[1]/ul[1]/div[2]/p[1]/text()
        price= price[0]
        content= price[1]
        a=price[2]
        b= price[-1]
        detail = [Naame,score,price,content,a,b]
        result.append(detail)
def join_all(sql_insert,vals,**dbinfo):
    try:
        connet = pymysql.connect(**dbinfo)
        cursor = connet.cursor()
        cursor.executemany(sql_insert,vals)
        connet.commit()
        print('添加成功!')
    except Exception as err:
        print(err)
        connet.rollback()
    cursor.close()
if __name__=="__main__":
    for page in range(1,16):
        url="https://book.douban.com/latest?subcat=%E5%85%A8%E9%83%A8&p={0}".format(str(page))
        parms ={
            "host":"127.0.0.1",
            "port":3306,
            "user":"root",
            "passwd":"123456",
            "db":"db",
            "charset":"utf8"
        }
        html=get_html(url)
        parse_html(html)
    sql_insert = "INSERT INTO db(Naame,score,price,content,a,b)\
                           Values(%s,%s,%s,%s,%s,%s)"
    join_all(sql_insert,result,**parms)
    print(result)

總結

本篇文章就到這裡瞭,希望能夠給你帶來幫助,也希望您能夠多多關註WalkonNet的更多內容!

推薦閱讀: