python 糗事百科實例
阿新 • • 發佈：2017-08-23
except 參考 string headers esp window com -c -s
/* */)[0].encode(‘utf-8‘)
username = site.xpath([email protected])[0].encode(‘utf-8‘)
#username = site.xpath(‘.//h2‘)[0].text
content = site.xpath(‘.//div[@class="content"]/span‘)[0].text.strip().encode(‘utf-8‘)
# 投票次數
vote = site.xpath(‘.//i‘)[0].text
#print site.xpath(‘.//*[@class="number"]‘)[0].text
# 評論信息
comments = site.xpath(‘.//i‘)[1].text
print imgUrl, username, content, vote, comments
except Exception, e:
print e爬取糗事百科段子，假設頁面的URL是 http://www.qiushibaike.com/8hr/page/1
要求：
-
使用requests獲取頁面信息，用XPath / re 做數據提取
-
獲取每個帖子裏的
用戶頭像鏈接、用戶姓名、段子內容、點贊次數和評論次數 -
保存到 json 文件內
參考代碼
#qiushibaike.py
#import urllib
#import re
#import chardet
import requests
from lxml import etree
page = 1
url = ‘http://www.qiushibaike.com/8hr/page/‘ + str(page)
headers = {
‘User-Agent‘: ‘Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/52.0.2743.116 Safari/537.36‘,
‘Accept-Language‘: ‘zh-CN,zh;q=0.8‘}
try:
response = requests.get(url, headers=headers)
resHtml = response.text
html = etree.HTML(resHtml)
result = html.xpath(‘//div[contains(@id,"qiushi_tag")]‘)
for site in result:
item = {}
imgUrl = site.xpath([email protected]python 糗事百科實例