BeautifulSoup解析网页

标签：lxml   imp   select   import   add   格式化   result   __str__   code   

from bs4 import BeautifulSoup
import requests

url = ‘http://dangjian.gmw.cn/node_11940.htm‘
html = requests.get(url).content
# prettify()用于格式化
soup = BeautifulSoup(html, ‘lxml‘)

# print(soup.prettify())
# print(soup.find_all(‘span‘, class_="channel-newsTime"))

resultSet = soup.find_all(‘ul‘, class_="channel-newsGroup")

urls = set()

for rs in resultSet:
    # url = rs.a[‘href‘]
    hrefs = rs.find_all(‘a‘)
    for href in hrefs:
        url = href[‘href‘]
        if url.startswith("http"):
            urls.add(url)
        else:
            urls.add("http://dangjian.gmw.cn/"+url)

print(urls)

for url in urls:
    html = requests.get(url).content
    soup = BeautifulSoup(html, ‘lxml‘)
    title = soup.find(id="articleTitle").string
    # parts = soup.find(id="contentMain")
    parts = soup.select("div #contentMain > p")
    content = ""
    for part in parts:
        content = content + part.string.__str__()
    print(title)
    print(content)

BeautifulSoup解析网页

标签：lxml   imp   select   import   add   格式化   result   __str__   code   

原文地址：https://www.cnblogs.com/cord/p/9452950.html