爬取淘寶美食信息並進行可視化展示

首先爬取淘寶美食信息

採用的爬取方法是selenium庫和pyquery庫，並將爬取到的美食信息存放到csv文件，具體代碼如下：

import re
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
from pyquery import PyQuery as pq
from config import *
import pymongo
import csv
import pandas as pd

client=pymongo.MongoClient(MONGO_URL)
db=client[MONGO_DB]

browser=webdriver.Chrome()
wait=WebDriverWait(browser,30)
product2=[]
def search():
    #try:
    url="https://www.taobao.com"
    browser.get(url)
    input = wait.until(EC.presence_of_element_located((By.CSS_SELECTOR, "#q")))
    submit=wait.until(EC.element_to_be_clickable((By.CSS_SELECTOR,'#J_TSearchForm > div.search-button > button')))
    input.send_keys('美食')
    submit.click()
    total=wait.until(EC.presence_of_element_located((By.CSS_SELECTOR,'#mainsrp-pager > div > div > div > div.total')))
    get_products()
    return total.text
    #except:
     #   search()

def next_page(page_number):
    try:
        input = wait.until(EC.presence_of_element_located((By.CSS_SELECTOR, "#mainsrp-pager > div > div > div > div.form > input")))
        submit = wait.until(EC.element_to_be_clickable((By.CSS_SELECTOR, '#mainsrp-pager > div > div > div > div.form > span.btn.J_Submit')))
        input.clear()
        input.send_keys(page_number)
        submit.click()
        wait.until(EC.text_to_be_present_in_element((By.CSS_SELECTOR,'#mainsrp-pager > div > div > div > ul > li.item.active > span'),str(page_number)))
        get_products()
    except:
        next_page(page_number)

def get_products():
    #wait.until(EC.presence_of_element_located((By.CSS_SELECTOR,'#mainsrp-itemlist.items.item')))#加載寶貝信息並等待
    html=browser.page_source
    doc=pq(html)
    items=doc('#mainsrp-itemlist .items .item').items()#得到所有寶貝的內容

    for item in items:
        product = []
        product.append(item.find('.title').text())
        product.append(item.find('.price').text())
        product.append(item.find('.deal-cnt').text()[:-3])
        product.append(item.find('.shop').text())
        product.append(item.find('.location').text())
        product2.append(product)
        print(product)
    #print(product2)
        #save_to_csv(product)

def save_to_mongo(result):
    try:
        if db[MONGO_TABLE].insert(result):
            print('存儲成功')
    except Exception:
        print('存儲失敗')

def save_to_csv():
    columns=['商品名稱','價格','銷量','店鋪','地點']
    save_file=pd.DataFrame(columns=columns,data=product2)
    save_file.to_csv('taobao2.csv',index=False,encoding='utf-8')

def main():
    total=search()
    total=int(re.compile('(\d+)').search(total).group(1)) #轉換爲數值型
    print(total)
    for i in range(2,10):
        next_page(i)
    save_to_csv()

if __name__=='__main__':
    main()