“Python爬虫案例：使用Selenium爬取阿里巴巴国际站”的版本间的差异
来自CloudWiki
| 第322行： | 第322行： | ||
==根据品类清单爬取全站商品== | ==根据品类清单爬取全站商品== | ||
| + | 这里的品类清单alibaba_categary.csv 由[[Python beautifulsoup4库 解析阿里巴巴分类网址]]获得。 | ||
| + | |||
| + | 运行时修改两个参数：start_class3 和start_page | ||
| + | |||
<nowiki>from selenium import webdriver | <nowiki>from selenium import webdriver | ||
from selenium.webdriver.common.by import By | from selenium.webdriver.common.by import By | ||
2020年8月11日 (二) 06:50的版本
目录
实训步骤
1.利用Selenium模拟访问网站
2.爬取页面商品信息
3.翻页，爬取下一页商品信息，直到完全爬完
实训过程
导入包及初始参数设置
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 selenium.common.exceptions import TimeoutException
from pyquery import PyQuery as pq
import re
import time
from bs4 import BeautifulSoup
import csv
#初始参数设置
driver = webdriver.Chrome("C:/Program Files (x86)/Google/Chrome/Application/chromedriver.exe")
wait = WebDriverWait(driver, 10)
#保存的时间和文件名
now_time =time.strftime("%Y%m%d%H%M%S", time.localtime())
file_name ='alibaba'+now_time+'.csv'
根据url模拟访问网站
#根据url模拟访问网站
def browse(url):
try:
driver.get(url)
scroll()
#time.sleep(60)#因为网站需验证码，故开始留出60秒的时间人工填验证码
print("访问成功！")
#total = wait.until(EC.presence_of_element_located((By.CSS_SELECTOR,'#mainsrp-pager > div > div > div > div.total')))
#get_products()
#return total.text
return "ok"
except TimeoutException:
return browse(url)
def scroll():#模拟页面下拉滚动函数
for i in range(1,11):
driver.execute_script("window.scrollTo(0,document.body.scrollHeight*"+str(i)+"/10)")
#time.sleep(2)
爬取商品信息
#得到商品信息
def get_products(page_number):
#wait.until(EC.presence_of_element_located((By.CSS_SELECTOR,'#mainsrp-itemlist .items .item')))
soup = BeautifulSoup(driver.page_source, "html.parser")
div_list = soup.find_all('div',class_ = 'organic-gallery-offer-outter')
print(len(div_list))
total =""
count=1
for i in div_list:
try:
total +=str(page_number)+"," #记录是第几页的信息
#商品图片信息
img = i.find('img')#商品图片
#print(str(count)+":"+img['src'])
total += img['src']+","
title= i.find('h4').get_text().strip()
title =title.replace(",","_")
#print((str(count)+":"+title))
total += title+","
#价格信息
detail = i.find('div', class_ = 'organic-gallery-offer-section__price') \
.find_all('span')
for d in detail:
di =d.get_text().strip()
di=di.replace(",","_")
#print(str(count)+":"+di)
total += di+","
#商家信息
supplier =i.find('div', class_ = 'organic-gallery-offer__seller-section').a
s_name =supplier['title'];s_name=s_name.replace(",","_")
s_href =supplier['href'];s_href=s_href.replace(",","_")
#print(s_name+","+s_href+",")
total += s_name+","+s_href+","
#国家和经营时间
country =i.find('span',class_ = 'seller-tag__country')
if(country is not None):
country=country['title']
else:
country="NoneType"
country = country.replace(",","_")
year =i.find('span',class_ = 'seller-tag__year').get_text().strip()
year = year.replace(",","_")
print(country+","+year+",")
total +=(country+","+year+",")
#换行
total += "\n"
except Exception as ex:
print("出现如下异常%s"%ex)
count=count+1
#print(title)
fw = open(file_name,"a",encoding="utf-8")
fw.write(total)
fw.close()
跳转到下一页
#跳转到下一页
def next_page(page_number):
try:
input =wait.until(EC.presence_of_element_located \
((By.XPATH,"//*[@id=\"root\"]/div/div[4]/div/div[2]/input")))
submit = wait.until(EC.element_to_be_clickable \
((By.XPATH,"//*[@id=\"root\"]/div/div[4]/div/div[2]/a")))
#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)))
print("现在开始爬第 "+ str(page_number)+" 页...")
print("现在开始爬第 "+ str(page_number)+" 页...")
print("现在开始爬第 "+ str(page_number)+" 页...")
scroll()#新页面 浏览
get_products(page_number)
except TimeoutException:
next_page(page_number)
main方法及调用
def main():
start = time.clock()
url ="http://www.alibaba.com/Animal-Products_pid100003006"
browse(url)
get_products(1)
#total = int(re.compile('(\d+)').search(total).group(1))
#爬取所有的数据用total+1
for i in range(2,6):
#next_page(i)
browse(url+"?page="+str(i))
get_products(i)
elapsed = (time.clock() - start)
print("Time used:",elapsed)
if __name__ == '__main__':
main()
全部代码
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 selenium.common.exceptions import TimeoutException
from pyquery import PyQuery as pq
import re
import time
from bs4 import BeautifulSoup
import csv
#初始参数设置
driver = webdriver.Chrome("C:/Program Files (x86)/Google/Chrome/Application/chromedriver.exe")
wait = WebDriverWait(driver, 10)
#保存的时间和文件名
now_time =time.strftime("%Y%m%d%H%M%S", time.localtime())
file_name ='alibaba'+now_time+'.csv'
#根据url模拟访问网站
def browse(url):
try:
driver.get(url)
scroll()
#time.sleep(60)#因为网站需验证码，故开始留出60秒的时间人工填验证码
print("访问成功！")
#total = wait.until(EC.presence_of_element_located((By.CSS_SELECTOR,'#mainsrp-pager > div > div > div > div.total')))
#get_products()
#return total.text
return "ok"
except TimeoutException:
return browse(url)
def scroll():#页面滚动函数
for i in range(1,11):
driver.execute_script("window.scrollTo(0,document.body.scrollHeight*"+str(i)+"/10)")
#time.sleep(2)
#得到商品信息
def get_products(page_number):
#wait.until(EC.presence_of_element_located((By.CSS_SELECTOR,'#mainsrp-itemlist .items .item')))
soup = BeautifulSoup(driver.page_source, "html.parser")
div_list = soup.find_all('div',class_ = 'organic-gallery-offer-outter')
print(len(div_list))
total =""
count=1
for i in div_list:
try:
total +=str(page_number)+"," #记录是第几页的信息
#商品图片信息
img = i.find('img')#商品图片
#print(str(count)+":"+img['src'])
total += img['src']+","
title= i.find('h4').get_text().strip()
title =title.replace(",","_")
#print((str(count)+":"+title))
total += title+","
#价格信息
detail = i.find('div', class_ = 'organic-gallery-offer-section__price') \
.find_all('span')
for d in detail:
di =d.get_text().strip()
di=di.replace(",","_")
#print(str(count)+":"+di)
total += di+","
#商家信息
supplier =i.find('div', class_ = 'organic-gallery-offer__seller-section').a
s_name =supplier['title'];s_name=s_name.replace(",","_")
s_href =supplier['href'];s_href=s_href.replace(",","_")
#print(s_name+","+s_href+",")
total += s_name+","+s_href+","
#国家和经营时间
country =i.find('span',class_ = 'seller-tag__country')
if(country is not None):
country=country['title']
else:
country="NoneType"
country = country.replace(",","_")
year =i.find('span',class_ = 'seller-tag__year').get_text().strip()
year = year.replace(",","_")
print(country+","+year+",")
total +=(country+","+year+",")
#换行
total += "\n"
except Exception as ex:
print("出现如下异常%s"%ex)
count=count+1
#print(title)
fw = open(file_name,"a",encoding="utf-8")
fw.write(total)
fw.close()
#跳转到下一页
def next_page(page_number):
try:
input =wait.until(EC.presence_of_element_located \
((By.XPATH,"//*[@id=\"root\"]/div/div[4]/div/div[2]/input")))
submit = wait.until(EC.element_to_be_clickable \
((By.XPATH,"//*[@id=\"root\"]/div/div[4]/div/div[2]/a")))
#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)))
print("现在开始爬第 "+ str(page_number)+" 页...")
print("现在开始爬第 "+ str(page_number)+" 页...")
print("现在开始爬第 "+ str(page_number)+" 页...")
scroll()#新页面 浏览
get_products(page_number)
except TimeoutException:
next_page(page_number)
def main():
start = time.clock()
url ="http://www.alibaba.com/Animal-Products_pid100003006"
browse(url)
get_products(1)
#total = int(re.compile('(\d+)').search(total).group(1))
#爬取所有的数据用total+1
for i in range(2,6):
#next_page(i)
browse(url+"?page="+str(i))
get_products(i)
elapsed = (time.clock() - start)
print("Time used:",elapsed)
if __name__ == '__main__':
main()
根据品类清单爬取全站商品
这里的品类清单alibaba_categary.csv 由Python beautifulsoup4库 解析阿里巴巴分类网址获得。
运行时修改两个参数：start_class3 和start_page
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 selenium.common.exceptions import TimeoutException
from pyquery import PyQuery as pq
import re
import time
from bs4 import BeautifulSoup
import csv
#初始参数设置
driver = webdriver.Chrome("C:/Program Files (x86)/Google/Chrome/Application/chromedriver.exe")
wait = WebDriverWait(driver, 10)
#保存的时间和文件名
now_time =time.strftime("%m%d%H%M%S", time.localtime())
start_class3 ='Holiday Gifts' #从这个(三级目录）开始爬取,默认从第一个三级目录开始爬取，可以更改
start_page = 1
end_page =start_page+20#此参数一般不改
file_name ='Alibaba_'+now_time+"_"+start_class3+"_" \
+str(start_page)+"_"+str(end_page) +'.csv'
begin =0;#标记是否开始爬
#根据url模拟访问网站
def browse(url):
try:
driver.get(url)
scroll()
#time.sleep(60)#因为网站需验证码，故开始留出60秒的时间人工填验证码
print("访问成功！")
#total = wait.until(EC.presence_of_element_located((By.CSS_SELECTOR,'#mainsrp-pager > div > div > div > div.total')))
#get_products()
#return total.text
return "ok"
except TimeoutException:
return browse(url)
def scroll():#页面滚动函数
for i in range(1,11):
driver.execute_script("window.scrollTo(0,document.body.scrollHeight*"+str(i)+"/10)")
time.sleep(0.25)
#time.sleep(2)
#得到商品信息
def get_products(page_number,class1,class2,class3):
#wait.until(EC.presence_of_element_located((By.CSS_SELECTOR,'#mainsrp-itemlist .items .item')))
soup = BeautifulSoup(driver.page_source, "html.parser")
div_list = soup.find_all('div',class_ = 'organic-gallery-offer-outter')
print(len(div_list))
total =""
count=1
for i in div_list:
try:
total +=str(page_number)+"," #记录是第几页的信息
total +=class1+","+class2+","+class3+"," #记录是其分属的1，2，3级目录
#商品图片信息
img = i.find('img')#商品图片
#print(str(count)+":"+img['src'])
total += img['src']+","
title= i.find('h4').get_text().strip()
title =title.replace(",","_")
#print((str(count)+":"+title))
total += title+","
#价格信息
detail = i.find('div', class_ = 'organic-gallery-offer-section__price') \
.find_all('span')
for d in detail:
di =d.get_text().strip()
di=di.replace(",","_")
#print(str(count)+":"+di)
total += di+","
#商家信息
supplier =i.find('div', class_ = 'organic-gallery-offer__seller-section').a
s_name =supplier['title'];s_name=s_name.replace(",","_")
s_href =supplier['href'];s_href=s_href.replace(",","_")
#print(s_name+","+s_href+",")
total += s_name+","+s_href+","
#国家和经营时间
country =i.find('span',class_ = 'seller-tag__country')
if(country is not None):
country=country['title']
else:
country="NoneType"
country = country.replace(",","_")
year =i.find('span',class_ = 'seller-tag__year')
if year is not None:
year =year.get_text().strip()
else:
year="NoneType"
year = year.replace(",","_")
#print(country+","+year+",")
total +=(country+","+year+",")
#换行
total += "\n"
except Exception as ex:
print("出现如下异常%s"%ex)
total += "\n"
count=count+1
#print(title)
return total#汇集每一页面的所有信息
#跳转到下一页
def next_page(page_number):
try:
input =wait.until(EC.presence_of_element_located \
((By.XPATH,"//*[@id=\"root\"]/div/div[4]/div/div[2]/input")))
submit = wait.until(EC.element_to_be_clickable \
((By.XPATH,"//*[@id=\"root\"]/div/div[4]/div/div[2]/a")))
#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)))
print("现在开始爬第 "+ str(page_number)+" 页...")
print("现在开始爬第 "+ str(page_number)+" 页...")
print("现在开始爬第 "+ str(page_number)+" 页...")
scroll()#新页面 浏览
get_products(page_number)
except TimeoutException:
next_page(page_number)
def read_category_file(start_class3):
cat_list =[]#创建类别网址列表
fp =open('alibaba_categary.csv',"rt")
#csv文件每行由class1,class2,class3,class3_url 这么几个字段
for line in fp: #文件对象可以直接迭代
d ={}
data =line.split(',')
d['class1'] =data[0]
d['class2'] =(data[1])
d['class3'] =(data[2])
d['url'] = data[3]
if d['class3'] =='View More':
continue
global begin
if d['class3'] ==start_class3:#到达start_class3才开始爬
begin=1;
elif begin==0:
continue;
cat_list.append(d)#将读取的每行信息添加到列表中
fp.close()
return cat_list
def get_category_info(class1,class2,class3,url):
#url ="http://www.alibaba.com/Animal-Products_pid100003006"
#total = int(re.compile('(\d+)').search(total).group(1))
info =""
for i in range(start_page,end_page):#(21,41);(41,61)
#next_page(i)
browse(url+"?page="+str(i))
info +=get_products(i,class1,class2,class3)
#将该品类信息写入文件
fw = open(file_name,"a",encoding="utf-8")
fw.write(info)
fw.close()
def main():
start = time.clock()
#'alibaba_categary.csv'
cat_file =read_category_file(start_class3)#从start_class3这个三级目录开始读取
for d in cat_file:
#爬取每一类别的商品信息，class1,class2,class3 分别指代1，2，3级目录
get_category_info(d['class1'],d['class2'],d['class3'],d['url'])
elapsed = (time.clock() - start)
print("Time used:",elapsed)
#'''
if __name__ == '__main__':
main()
