####开发工具
- Python版本：3.6 - 相关模块： ``` 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 * ``` ####config文件 ``` SERVICE_ARGS = ['--load-images=false', '--disk-cache=true'] KEYWORD = '美食' ``` ####全部代码 ``` '''利用selenium爬取淘宝美食网页内容'''
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 *
driver = webdriver.PhantomJS(service_args=SERVICE_ARGS) # driver = webdriver.Chrome() wait = WebDriverWait(driver, 10)
driver.set_window_size(1400,900) #有这这句话就是可以爬取到网页的内容，没有的话就出现TimeOut错误
def search(): print('正在搜索') try: driver.get('http://www.taobao.com') s_input = wait.until(EC.presence_of_element_located((By.CSS_SELECTOR,'#q'))) sumbit = wait.until(EC.element_to_be_clickable((By.CSS_SELECTOR,'#J_TSearchForm > div.search-button > button'))) s_input.send_keys(KEYWORD) sumbit.click() totle = wait.until(EC.presence_of_element_located((By.CSS_SELECTOR,'#mainsrp-pager > div > div > div > div.total'))) get_products() return totle.text except TimeoutException: print('TimeOut') return search()
def next_page(page_number): print('正在翻页', page_number) try: s_input = wait.until(EC.presence_of_element_located((By.CSS_SELECTOR, '#mainsrp-pager > div > div > div > div.form > input'))) sumbit = wait.until(EC.element_to_be_clickable((By.CSS_SELECTOR, '#mainsrp-pager > div > div > div > div.form > span.btn.J_Submit'))) s_input.clear() s_input.send_keys(page_number) sumbit.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: print('TimeOut') next_page(page_number)
def get_products(): wait.until(EC.presence_of_element_located((By.CSS_SELECTOR,'#mainsrp-itemlist .items .item'))) html = driver.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)
def main(): try: totle = search() totle = int(re.compile('(\d+)').search(totle).group(1)) for num in range(2,totle + 1): next_page(num) except Exception as e: print(e) finally: #最后执行的操作 driver.close()
if __name__ == '__main__': main() ```
