使用selenium爬取淘宝店铺信息 - 好文

使用selenium +PhantomJS()/Chrome爬取淘宝页面，存储到mongdb中

使用config进行一些设置

MONGO_URL = 'localhost'
MONGO_DB = 'taobao'
MONGO_TABLE = 'product'

# 将图片设定为不下载
SERVICE_ARGS = ['--load-images=false', '--disk-cache=true']

# 搜索名称
KEYWORD = '情人节礼物'

在编写代码的时候要注意，可以先使用Chrome 运行，当将代码调试完毕后，在改为PhantomJS

代码如下

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
from pyquery import PyQuery as pq
from config import *
import pymongo

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

browser = webdriver.PhantomJS()
wait = WebDriverWait(browser, 10)

browser.set_window_size(1400, 900)

def search():
print('正在搜索')
try:
browser.get('https://www.taobao.com')
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(KEYWORD)
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 TimeoutException:
return search()

def next_page(page_number):
print('正在翻页', 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 TimeoutException:
next_page(page_number)

def get_products():
wait.until(EC.presence_of_element_located((By.CSS_SELECTOR,
'#mainsrp-itemlist .items .item')))
html = browser.page_source
doc = pq(html)
items = doc('#mainsrp-itemlist .items .item').items()
for item in items:
product = {
'image': item.find('.pic .img').attr('src'),
'price': item.find('.price').text(),
'deal': item.find('.deal-cnt').text()[:-3],
'title': item.find('.title').text(),
'shop': item.find('.shop').text(),
'location': item.find('.location').text()
}
print(product)
save_to_mongo(product)

def save_to_mongo(result):
try:
if db[MONGO_TABLE].insert(result):
print('存储到MONGODB成功', result)
except Exception:
print('存储到MONGODB失败', result)

def main():
try:
total = search()
total = int(re.compile('(\d+)').search(total).group(1))
for i in range(2, total + 1):
next_page(i)
except Exception:
print('出错啦')
finally:
browser.close()

if __name__ == '__main__':
main()