import requests
from bs4 import BeautifulSoup
import bs4
def get_html(url,headers):
r = requests.get(url,headers=headers)
r.encoding = r.apparent_encoding
return r.text
def get_pages(html):
soup = BeautifulSoup(html,‘html.parser‘)
all_topics=soup.find_all(‘tr‘)[1:]
for each_topic in all_topics:
#print(each_topic)
topic_times = each_topic.find(‘td‘,class_=‘last‘)#搜索指数
topic_rank = each_topic.find(‘td‘,class_=‘first‘)#排名
topic_name = each_topic.find(‘td‘,class_=‘keyword‘)#标题目
if topic_rank != None and topic_name!=None and topic_times!=None:
topic_rank = each_topic.find(‘td‘,class_=‘first‘).get_text().replace(‘ ‘,‘‘).replace(‘\n‘,‘‘)
topic_name = each_topic.find(‘td‘,class_=‘keyword‘).get_text().replace(‘ ‘,‘‘).replace(‘\n‘,‘‘)