[Python] 纯文本查看 复制代码import jsonimport re
import requests
from urllib.parse import urlencode
from bs4 import BeautifulSoup
from requests.exceptions import RequestException
def get_page_index(offset,keyword):
data = {
'offset': offset,
'format': 'json',
'keyword': keyword,
'autoload':'true',
'ount': '20',
'cur_tab': 1 ,
'from':'search_tab'
}
url = 'https://www.toutiao.com/search_content/?' + urlencode(data)
response = requests.get(url)
try:
if response.status_code ==200:
return response.text
return None
except RequestException:
print('get failed!')
return None
def parse_ge_index(html):
data = json.loads(html)
if data and 'data' in data.keys():
for item in data.get('data'):
yield item.get('article_url')
def get_page_detail(url):
if url == 'http://None':
return None
response = requests.get(url)
if response.status_code == 200:
return response.text
return None
def parse_page_detail(html):
soup = BeautifulSoup(html,'lxml')
title = soup.select('title')[0].get_text()
image_pattern = re.compile('gallery: JSON.parse(.*?);',re.S)
result = re.search(image_pattern,html)
if result:
print(result.group(1))
def main():
html = get_page_index(0,'街拍')
for url in parse_ge_index(html):
print(url)
html = get_page_detail(url)
if __name__ == '__main__':
main()