Selenium 爬取淘宝数据

1、项目流程

---

2、中心调度

#中心调度

defmain():

try:

total = search()

total =int(re.compile('.*?(\d+).*?').search(total).group(1))

foriinrange(2,total+1):

next_page(i)

exceptExceptionase:

print('异常')

finally:

browser.close()

---

3、模拟查询

#根据关键字查询

defsearch():

try:

browser.get('https://www.taobao.com/')

#直到搜索框加载出

input_search = wait.until(EC.presence_of_element_located((By.ID,'q')))

#直到搜索按钮可以点击

submit_button = wait.until(EC.element_to_be_clickable((By.CLASS_NAME,'btn-search')))

input_search.send_keys(KEYWORDS)

submit_button.click()

total = wait.until(EC.presence_of_element_located((By.CSS_SELECTOR,'div.wraper div.total')))

get_products()

returntotal.text

exceptTimeoutExceptionase:

print('响应超时')

---

4、下一页的操作

#下一页爬取

defnext_page(index):

try:

input = wait.until(EC.presence_of_element_located((By.CSS_SELECTOR,'#mainsrp-pager div.form > input')))

submit = wait.until(EC.element_to_be_clickable((By.CSS_SELECTOR,'#mainsrp-pager div.form > span.btn.J_Submit')))

input.clear()

input.send_keys(index)

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(index)))

get_products()

exceptNoSuchElementExceptionase:

print('元素未加载')

returnnext_page(index)

---

5、商品信息的解析

#获取一页上所有的商品

defget_products():

wait.until(EC.presence_of_element_located((By.CSS_SELECTOR,"#mainsrp-itemlist .items .item")))

html = browser.page_source

doc = PyQuery(html)

items = doc('.m-itemlist .items .item').items()

foriteminitems:

product = {

'image':item.find('.pic-link .img').attr('data-src'),

'price':float(item.find('.price').text()[2:]),

'deal':item.find('.deal-cnt').text()[:-3],

'title':item.find('.title').text(),

'shop':item.find('.shop').text(),

'location':item.find('.location').text(),

'keywords':KEYWORDS

}

save_to_mongo(product=product)

---

6、完整代码

#!/usr/bin/python

# -*- coding: utf-8 -*-

importpymongo

importre

frompyqueryimportPyQuery

fromseleniumimportwebdriver

fromselenium.webdriver.common.byimportBy

fromselenium.webdriver.support.uiimportWebDriverWait

fromselenium.webdriver.supportimportexpected_conditionsasEC

fromselenium.common.exceptionsimportTimeoutException,NoSuchElementException

fromsettingimport*

client = pymongo.MongoClient(MONGO_HOST)

db = client[MONGO_DB]

browser = webdriver.Chrome()

wait = WebDriverWait(browser,10)

#根据关键字查询

defsearch():

try:

browser.get('https://www.taobao.com/')

#直到搜索框加载出

input_search = wait.until(EC.presence_of_element_located((By.ID,'q')))

#直到搜索按钮可以点击

submit_button = wait.until(EC.element_to_be_clickable((By.CLASS_NAME,'btn-search')))

input_search.send_keys(KEYWORDS)

submit_button.click()

total = wait.until(EC.presence_of_element_located((By.CSS_SELECTOR,'div.wraper div.total')))

get_products()

returntotal.text

exceptTimeoutExceptionase:

print('响应超时')

#下一页爬取

defnext_page(index):

try:

input = wait.until(EC.presence_of_element_located((By.CSS_SELECTOR,'#mainsrp-pager div.form > input')))

submit = wait.until(EC.element_to_be_clickable((By.CSS_SELECTOR,'#mainsrp-pager div.form > span.btn.J_Submit')))

input.clear()

input.send_keys(index)

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(index)))

get_products()

exceptNoSuchElementExceptionase:

print('元素未加载')

returnnext_page(index)

#获取一页上所有的商品

defget_products():

wait.until(EC.presence_of_element_located((By.CSS_SELECTOR,"#mainsrp-itemlist .items .item")))

html = browser.page_source

doc = PyQuery(html)

items = doc('.m-itemlist .items .item').items()

foriteminitems:

product = {

'image':item.find('.pic-link .img').attr('data-src'),

'price':float(item.find('.price').text()[2:]),

'deal':item.find('.deal-cnt').text()[:-3],

'title':item.find('.title').text(),

'shop':item.find('.shop').text(),

'location':item.find('.location').text(),

'keywords':KEYWORDS

}

save_to_mongo(product=product)

#保存至mongoDB

defsave_to_mongo(product):

try:

ifdb[MONGO_TABLE].insert(product):

print('保存成功', product)

exceptException:

print('保存失败')

#中心调度

defmain():

try:

total = search()

total =int(re.compile('.*?(\d+).*?').search(total).group(1))

foriinrange(2,total+1):

next_page(i)

exceptExceptionase:

print('异常')

finally:

browser.close()

if__name__=='__main__':

main()

7、运行结果