使用selenium +PhantomJS()/Chrome爬取 淘宝页面
首先创建一个config.py的文件。在里面做些适当配置：
# 缓存模式
SERVICE_ARGS = ['--disk-cache=true']
# 搜索名称
KEYWORD = '情人节礼物'
在主文件中编写代码：
# coding:utf-8
import re
from pprint import pprint
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 *
browser = webdriver.PhantomJS(service_args=SERVICE_ARGS)
wait = WebDriverWait(browser, 10)
browser.set_window_size(1400, 900)
def serach():
print('正在搜索')
try:
browser.get("https://www.taobao.com")
# 等待输入框加载完毕
input = wait.until(
EC.presence_of_element_located((By.CSS_SELECTOR, '#q'))
)
# 等待确定键加载完毕
submit = wait.until(
EC.element_to_be_clickable((By.CSS_SELECTOR, '#J_TSearchForm > div.search-button > button'))
)
# 向输入框填入内容
input.send_keys(KEYWORD)
# 点击搜索按钮
submit.click()
# 得出页面数据
total = wait.until(
EC.presence_of_element_located((By.CSS_SELECTOR, '#mainsrp-pager > div > div > div > div.total'))
)
get_product()
return total.text
except TimeoutError:
return serach()
def get_product():
# 得到每个栏目的玩家信息
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 = {
'price': item.find('.price').text(),
'deal': item.find('.deal-cnt').text()[:-3],
'name': item.find('.title').text(),
'shop': item.find('.shop').text(),
'location': item.find('.location').text()
}
pprint(product)
def next_page(page_count):
print('正在翻页', page_count)
try:
input = wait.until(
EC.presence_of_element_located((By.CSS_SELECTOR, '#mainsrp-pager > div > div > div > div.form > input'))
)
# 等待确定键加载完毕
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_count)
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_count)
))
get_product()
except TimeoutError:
next_page(page_count)
def main():
try:
total = serach()
total = int(re.compile(r'(\d+)').search(total).group(1))
# print(total)
for i in range(2, total + 1):
next_page(i)
except Exception:
print('出现异常')
finally:
browser.close()
if __name__ == '__main__':
main()
部分效果图如下：
