python数据抓取3种方法总结

from get_html import download

url = 'https://guojiadiqu.bmcx.com/AFG__guojiayudiqu/'
page_content = download(url)

from get_html import download
import re

url = 'https://guojiadiqu.bmcx.com/AFG__guojiayudiqu/'
page_content = download(url)
country = re.findall('class="h2dabiaoti">(.*?)</h2>', page_content) #注意返回的是list
survey_data = re.findall('<tr><td bgcolor="#FFFFFF" id="wzneirong">(.*?)</td></tr>', page_content)
survey_info_list = re.findall('<p>　　(.*?)</p>', survey_data[0])
survey_info = ''.join(survey_info_list)
print(country[0],survey_info)

from get_html import download
from bs4 import BeautifulSoup

url = 'https://guojiadiqu.bmcx.com/AFG__guojiayudiqu/'
html = download(url)
#创建 beautifulsoup 对象
soup = BeautifulSoup(html,"html.parser")
#搜索
country = soup.find(attrs={'class':'h2dabiaoti'}).text
survey_info = soup.find(attrs={'id':'wzneirong'}).text
print(country,survey_info)

from get_html import download
from lxml import etree #解析树

url = 'https://guojiadiqu.bmcx.com/AFG__guojiayudiqu/'
page_content = download(url)
selector = etree.HTML(page_content)#可进行xpath解析
country_select = selector.xpath('//*[@id="main_content"]/h2') #返回列表
for country in country_select:
 print(country.text)
survey_select = selector.xpath('//*[@id="wzneirong"]/p')
for survey_content in survey_select:
 print(survey_content.text,end='')