欧美bbbwbbbw肥妇,免费乱码人妻系列日韩,一级黄片

Python爬蟲實(shí)戰(zhàn)之爬取某寶男裝信息

 更新時間：2021年12月02日 10:21:13   作者：編程簡單學(xué)  
網(wǎng)絡(luò)爬蟲是一種按照一定的規(guī)則自動瀏覽、檢索網(wǎng)頁信息的程序或者腳本。網(wǎng)絡(luò)爬蟲能夠自動請求網(wǎng)頁，并將所需要的數(shù)據(jù)抓取下來。本文將為大家介紹如何利用爬蟲獲取某寶男裝信息，感興趣的小伙伴可以了解一下

知識點(diǎn)介紹

本次爬取用到的知識點(diǎn)有:

1. selenium

2. pymysql

3? pyquery

實(shí)現(xiàn)步驟

1. 分析目標(biāo)網(wǎng)站

1. 打開某寶首頁, 輸入"男裝"后點(diǎn)擊"搜索", 則跳轉(zhuǎn)到"男裝"的搜索界面.

2. 空白處"右擊"再點(diǎn)擊"檢查"審查網(wǎng)頁元素, 點(diǎn)擊"Network".

1) 找到對應(yīng)的URL, URL里的參數(shù)正是Query String Parameters的參數(shù), 且請求方式是GET

2) 我們請求該URL得到內(nèi)容就是"Response"里的內(nèi)容, 那么點(diǎn)擊它來確認(rèn)信息.

3) 下拉看到"男裝"字樣, 那么再往下找, 并沒有發(fā)現(xiàn)有關(guān)"男裝"的商品信息.

4) 任意復(fù)制一個商品信息, 空白處右擊再點(diǎn)擊"查看網(wǎng)頁源代碼", 在源碼查找該商品, 即可看到該商品的信息.

5) 對比網(wǎng)頁源代碼和"Response"響應(yīng)內(nèi)容, 發(fā)現(xiàn)源代碼<script>..........</script>中的商品信息被替換, 這便是采用了JS加密

6) 如果去請求上面的URL, 得到的則是加密過的信息, 這時就可以利用Selenium庫來模擬瀏覽器, 進(jìn)而得到商品信息.

2. 獲取單個商品界面

請求網(wǎng)站

# -*- coding: utf-8 -*-
from selenium import webdriver   #從selenium導(dǎo)入瀏覽器驅(qū)動
browser = webdriver.Chrome()   #聲明驅(qū)動對象, 即Chrome瀏覽器
def get_one_page():
    '''獲取單個頁面'''
    browser.get("https://www.xxxxx.com")  #請求網(wǎng)站

輸入"男裝", 在輸入之前, 需要判斷輸入框是否存在, 如果存在則輸入"男裝", 不存在則等待顯示成功.

# -*- coding: utf-8 -*-
from selenium import webdriver  
from selenium.webdriver.common.by import By                       #導(dǎo)入元素定位方法模塊
from selenium.webdriver.support.ui import WebDriverWait           #導(dǎo)入等待判斷模塊
from selenium.webdriver.support import expected_conditions as EC  #導(dǎo)入判斷條件模塊
browser = webdriver.Chrome()   
def get_one_page():
    '''獲取單個頁面'''
    browser.get("https://www.xxxxx.com") 
    input = WebDriverWait(browser,10).until(                       #等待判斷
        EC.presence_of_element_located((By.CSS_SELECTOR,"#q")))    #若輸入框顯示成功,則獲取,否則等待
    input.send_keys("男裝")                                         #輸入商品名稱

下一步就是點(diǎn)擊"搜索"按鈕, 按鈕具有屬性: 可點(diǎn)擊, 那么加入判斷條件.

# -*- coding: utf-8 -*-
from selenium import webdriver   
from selenium.webdriver.common.by import By  
from selenium.webdriver.support.ui import WebDriverWait  
from selenium.webdriver.support import expected_conditions as EC  
browser = webdriver.Chrome()   
def get_one_page():
    '''獲取單個頁面'''
    browser.get("https://www.xxxxx.com")  
    input = WebDriverWait(browser,10).until(                       
        EC.presence_of_element_located((By.CSS_SELECTOR,"#q")))    #
    input.send_keys("男裝")   
    button = WebDriverWait(browser,10).until(                                                        #等待判斷
        EC.element_to_be_clickable((By.CSS_SELECTOR,"#J_TSearchForm > div.search-button > button"))) #若按鈕可點(diǎn)擊, 則獲取, 否則等待
    button.click()                                                                                   #點(diǎn)擊按鈕

獲取總的頁數(shù), 同樣加入等待判斷.

# -*- coding: utf-8 -*-
 
import re
from selenium import webdriver
from selenium.common.exceptions import TimeoutException
from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
browser = webdriver.Chrome()
def get_one_page():
    '''獲取單個頁面'''
    browser.get("https://www.xxxxx.com")
    input = WebDriverWait(browser, 10).until(
        EC.presence_of_element_located((By.CSS_SELECTOR, "#q")))
    input.send_keys("男裝")
    button = WebDriverWait(browser, 10).until(
        EC.element_to_be_clickable(
            (By.CSS_SELECTOR, "#J_TSearchForm > div.search-button > button")))
    button.click()  
    pages = WebDriverWait(browser, 10).until(  # 等待判斷
        EC.presence_of_element_located(
            (By.CSS_SELECTOR, "#mainsrp-pager > div > div > div > div.total")))  # 若總頁數(shù)加載成功,則獲取總頁數(shù),否則等待 
    return pages.text
def main():
    pages = get_one_page()
    print(pages)
if __name__ == '__main__':
    main()

打印出來的不是我們想要的結(jié)果, 利用正則表達(dá)式獲取, 最后再利用try...except捕捉異常

# -*- coding: utf-8 -*-
import re
from selenium import webdriver   
from selenium.common.exceptions import TimeoutException   
from selenium.webdriver.common.by import By  
from selenium.webdriver.support.ui import WebDriverWait  
from selenium.webdriver.support import expected_conditions as EC  
browser = webdriver.Chrome()  
def get_one_page():
    '''獲取單個頁面'''
    try:
        browser.get("https://www.xxxxx.com")  
        input = WebDriverWait(browser,10).until(
　　　　　　EC.presence_of_element_located((By.CSS_SELECTOR,"#q")))    
        input.send_keys("男裝")   
        button = WebDriverWait(browser,10).until(
　　　　　　EC.element_to_be_clickable((By.CSS_SELECTOR,"#J_TSearchForm > div.search-button > button"))) 
        button.click()            
        pages = WebDriverWait(browser,10).until(
　　　　　　EC.presence_of_element_located((By.CSS_SELECTOR,"#mainsrp-pager > div > div > div > div.total")))  
        return pages.text
    except TimeoutException:
        return get_one_page()   #如果超時,繼續(xù)獲取
def main():
    pages = get_one_page()
    pages = int(re.compile("(\d+)").findall(pages)[0]) #采用正則表達(dá)式提取文本中的總頁數(shù)
    print(pages)
if __name__ == '__main__':
    main()

關(guān)于Selenium的更多內(nèi)容,可參看官方文檔https://selenium-python.readthedocs.io/waits.html

3. 獲取多個商品界面

采用獲取"到第 頁"輸入框方式, 切換到下一頁, 同樣是等待判斷

需要注意的是, 最后要加入判斷: 高亮是否是當(dāng)前頁??

def get_next_page(page):
    try:
        input = WebDriverWait(browser, 10).until(                                                                                         
            EC.presence_of_element_located((By.CSS_SELECTOR, "#mainsrp-pager > div > div > div > div.form > input")))                       # 若輸入框加載成功,則獲取,否則等待
        input.send_keys(page)                                                                                                               # 輸入頁碼
        button = WebDriverWait(browser, 10).until(                                                                                       
            EC.element_to_be_clickable((By.CSS_SELECTOR, "#mainsrp-pager > div > div > div > div.form > span.btn.J_Submit")))               # 若按鈕可點(diǎn)擊,則獲取,否則等待
        button.click()                                                                                                                      # 點(diǎn)擊按鈕
        WebDriverWait(browser,10).until(
            EC.text_to_be_present_in_element((By.CSS_SELECTOR,"#mainsrp-pager > div > div > div > ul > li.item.active > span"),str(page)))  # 判斷高亮是否是當(dāng)前頁
    except TimeoutException:                                                                                                                # 超時, 繼續(xù)請求
        return get_next_page(page)
def main():
    pages = get_one_page()
    pages = int(re.compile("(\d+)").findall(pages)[0])
    for page in range(1,pages+1):
        get_next_page(page)
if __name__ == '__main__':
    main()

4. 獲取商品信息

首先, 判斷信息是否加載成功, 緊接著獲取源碼并初始化, 進(jìn)而解析.

需要注意的是, 在"get_one_page"和"get_next_page"中調(diào)用之后, 才可執(zhí)行

def get_info():
    """獲取詳情"""
    WebDriverWait(browser,20).until(EC.presence_of_element_located((
        By.CSS_SELECTOR,"#mainsrp-itemlist .items .item")))                #判斷商品信息是否加載成功
    text = browser.page_source                                             #獲取網(wǎng)頁源碼
    html = pq(text)                                                        #初始化網(wǎng)頁源碼
    items = html('#mainsrp-itemlist .items .item').items()                 #采用items方法會得到生成器
    for item in items:                                                     #遍歷每個節(jié)點(diǎn)對象
        data = []
        image = item.find(".pic .img").attr("data-src")                    #用find方法查找子孫節(jié)點(diǎn),用attr方法獲取屬性名稱
        price = item.find(".price").text().strip().replace("\n","")        #用text方法獲取文本,strip()去掉前后字符串,默認(rèn)是空格
        deal = item.find(".deal-cnt").text()[:-2]
        title = item.find(".title").text().strip()
        shop = item.find(".shop").text().strip()
        location = item.find(".location").text()
        data.append([shop, location, title, price, deal, image])
        print(data)

5. 保存到MySQL數(shù)據(jù)庫

def save_to_mysql(data):
    """存儲到數(shù)據(jù)庫"""
    # 創(chuàng)建數(shù)據(jù)庫連接對象
    db= pymysql.connect(host = "localhost",user = "root",password = "password",port = 3306, db = "spiders",charset = "utf8")
    # 獲取游標(biāo)
    cursor = db.cursor()
    #創(chuàng)建數(shù)據(jù)庫
    cursor.execute("CREATE TABLE IF NOT EXISTS {0}(shop VARCHAR(20),location VARCHAR(10),title VARCHAR(255),price VARCHAR(20),deal VARCHAR(20), image VARCHAR(255))".format("男裝"))
    #SQL語句
    sql = "INSERT INTO {0} values(%s,%s,%s,%s,%s,%s)".format("男裝")
    try:
            #傳入?yún)?shù)sql,data
        if cursor.execute(sql,data):
            #插入數(shù)據(jù)庫
            db.commit()
            print("********已入庫**********")
    except:
        print("#########入庫失敗#########")
        #回滾,相當(dāng)什么都沒做
        db.rollback()
    #關(guān)閉數(shù)據(jù)庫
    db.close()

完整代碼

# -*- coding: utf-8 -*-
'''
有需要Python學(xué)習(xí)資料的小伙伴嗎?小編整理一套Python資料和PDF，感興趣者可以加學(xué)習(xí)群：548377875，反正閑著也是閑著呢，不如學(xué)點(diǎn)東西啦~~
'''
import re
import pymysql
from selenium import webdriver   
from selenium.common.exceptions import TimeoutException
from selenium.webdriver.common.by import By  
from selenium.webdriver.support.ui import WebDriverWait  
from selenium.webdriver.support import expected_conditions as EC  
from pyquery import PyQuery as pq
browser = webdriver.Chrome()  
def get_one_page(name):
    '''獲取單個頁面'''
    print("-----------------------------------------------獲取第一頁-------------------------------------------------------")
    try:
        browser.get("https://www.xxxxx.com")  
        input = WebDriverWait(browser,10).until(                       
             EC.presence_of_element_located((By.CSS_SELECTOR,"#q")))   
        input.send_keys(name)   
        button = WebDriverWait(browser,10).until(                                                        
             EC.element_to_be_clickable((By.CSS_SELECTOR,"#J_TSearchForm > div.search-button > button"))) 
        button.click()            
        pages = WebDriverWait(browser,10).until(                                                           
          EC.presence_of_element_located((By.CSS_SELECTOR,"#mainsrp-pager > div > div > div > div.total")))  
        print("----即將解析第一頁信息----")
        get_info(name)
        print("----第一頁信息解析完成----")
        return pages.text
    except TimeoutException:
        return get_one_page(name)   
def get_next_page(page,name):
     """獲取下一頁"""
     print("---------------------------------------------------正在獲取第{0}頁----------------------------------------".format(page))
     try:
        input = WebDriverWait(browser, 10).until(
             EC.presence_of_element_located((By.CSS_SELECTOR, "#mainsrp-pager > div > div > div > div.form > input")))                       
        input.send_keys(page)                                                                                                               
        button = WebDriverWait(browser, 10).until(
            EC.element_to_be_clickable((By.CSS_SELECTOR, "#mainsrp-pager > div > div > div > div.form > span.btn.J_Submit")))               
        button.click()                                                                                                                      
        WebDriverWait(browser,10).until(
             EC.text_to_be_present_in_element((By.CSS_SELECTOR,"#mainsrp-pager > div > div > div > ul > li.item.active > span"),str(page)))  
        print("-----即將解析第{0}頁信息-----".format(page))
        get_info(name)
        print("-----第{0}頁信息解析完成-----".format(page))
     except TimeoutException:                                                                                                                
        return get_next_page(page,name)
def get_info(name):
    """獲取詳情""" 
    WebDriverWait(browser,20).until(EC.presence_of_element_located((
        By.CSS_SELECTOR,"#mainsrp-itemlist .items .item")))                
    text = browser.page_source                                             
    html = pq(text)                                                        
    items = html('#mainsrp-itemlist .items .item').items()                 
    for item in items:                                                     
        data = []
        image = item.find(".pic .img").attr("data-src")                    
        price = item.find(".price").text().strip().replace("\n","")        
        deal = item.find(".deal-cnt").text()[:-2]
        title = item.find(".title").text().strip()
        shop = item.find(".shop").text().strip()
        location = item.find(".location").text()
        data.append([shop, location, title, price, deal, image])
        for dt in data:
            save_to_mysql(dt,name)
def save_to_mysql(data,name):
    """存儲到數(shù)據(jù)庫"""
    db= pymysql.connect(host = "localhost",user = "root",password = "password",port = 3306, db = "spiders",charset = "utf8")
    cursor = db.cursor()
    cursor.execute("CREATE TABLE IF NOT EXISTS {0}(shop VARCHAR(20),location VARCHAR(10),title VARCHAR(255),price VARCHAR(20),deal VARCHAR(20), image VARCHAR(255))".format(name))
    sql = "INSERT INTO {0} values(%s,%s,%s,%s,%s,%s)".format(name)
    try:
        if cursor.execute(sql,data):
            db.commit()
         print("********已入庫**********")
    except:
        print("#########入庫失敗#########")
        db.rollback()
    db.close()
def main(name):
    pages = get_one_page(name)
    pages = int(re.compile("(\d+)").findall(pages)[0])
    for page in range(1,pages+1):
       get_next_page(page,name)
if __name__ == '__main__':
    name = "男裝"
    main(name)

到此這篇關(guān)于Python爬蟲實(shí)戰(zhàn)之爬取某寶男裝信息的文章就介紹到這了,更多相關(guān)Python 爬取信息內(nèi)容請搜索腳本之家以前的文章或繼續(xù)瀏覽下面的相關(guān)文章希望大家以后多多支持腳本之家！

相關(guān)文章

最新評論