用python代码实现分别采用request、selenium、scrapy爬取东方财富网上的热门数据、特色数据、沪深港通数据等。

1. 使用 requests 爬取东方财富网热门数据：

import requests
from bs4 import BeautifulSoup

url = 'http://finance.eastmoney.com/'

res = requests.get(url)
soup = BeautifulSoup(res.text, 'html.parser')

hot_news = soup.find_all('div', {'class': 'hotNews'})[0]
hot_news_titles = hot_news.find_all('a')

for title in hot_news_titles:
    print(title.text.strip())

2. 使用 Selenium 爬取东方财富网热门数据：

from selenium import webdriver

url = 'http://finance.eastmoney.com/'

driver = webdriver.Chrome()
driver.get(url)

hot_news = driver.find_element_by_class_name('hotNews')
hot_news_titles = hot_news.find_elements_by_tag_name('a')

for title in hot_news_titles:
    print(title.text.strip())

driver.quit()

3. 使用 Scrapy 爬取东方财富网热门数据：

import scrapy


class FinanceSpider(scrapy.Spider):
    name = 'finance'

    start_urls = [
        'http://finance.eastmoney.com/'
    ]

    def parse(self, response):
        hot_news = response.css('.hotNews')
        hot_news_titles = hot_news.css('a::text').getall()

        for title in hot_news_titles:
            yield {
                'title': title.strip()
            }

4. 使用 requests 爬取东方财富网特色数据：

import requests
from bs4 import BeautifulSoup

url = 'http://finance.eastmoney.com/special/00095/'

res = requests.get(url)
soup = BeautifulSoup(res.text, 'html.parser')

special_news = soup.find_all('div', {'class': 'listSpecial'})[0]
special_news_titles = special_news.find_all('a')

for title in special_news_titles:
    print(title.text.strip())

5. 使用 Selenium 爬取东方财富网特色数据：

from selenium import webdriver

url = 'http://finance.eastmoney.com/special/00095/'

driver = webdriver.Chrome()
driver.get(url)

special_news = driver.find_element_by_class_name('listSpecial')
special_news_titles = special_news.find_elements_by_tag_name('a')

for title in special_news_titles:
    print(title.text.strip())

driver.quit()

6. 使用 Scrapy 爬取东方财富网特色数据：

import scrapy


class FinanceSpecialSpider(scrapy.Spider):
    name = 'finance_special'

    start_urls = [
        'http://finance.eastmoney.com/special/00095/'
    ]

    def parse(self, response):
        special_news = response.css('.listSpecial')
        special_news_titles = special_news.css('a::text').getall()

        for title in special_news_titles:
            yield {
                'title': title.strip()
            }

7. 使用 requests 爬取东方财富网沪深港通数据：

import requests
from bs4 import BeautifulSoup

url = 'http://finance.eastmoney.com/hsgt/index.html'

res = requests.get(url)
soup = BeautifulSoup(res.text, 'html.parser')

hs_con = soup.find_all('div', {'class': 'hs_con'})[0]
hs_con_titles = hs_con.find_all('a')

for title in hs_con_titles:
    print(title.text.strip())

8. 使用 Selenium 爬取东方财富网沪深港通数据：

from selenium import webdriver

url = 'http://finance.eastmoney.com/hsgt/index.html'

driver = webdriver.Chrome()
driver.get(url)

hs_con = driver.find_element_by_class_name('hs_con')
hs_con_titles = hs_con.find_elements_by_tag_name('a')

for title in hs_con_titles:
    print(title.text.strip())

driver.quit()

9. 使用 Scrapy 爬取东方财富网沪深港通数据：

import scrapy


class FinanceHSGTSpider(scrapy.Spider):
    name = 'finance_hsgt'

    start_urls = [
        'http://finance.eastmoney.com/hsgt/index.html'
    ]

    def parse(self, response):
        hs_con = response.css('.hs_con')
        hs_con_titles = hs_con.css('a::text').getall()

        for title in hs_con_titles:
            yield {
                'title': title.strip()
            }