爬取论坛标题与链接存入 excel

爬取后，方便大家直接在 excel 中找到已分享的经验的标题与对应的链接。
代码如下：

import requests, xlwt
from bs4 import BeautifulSoup
from lxml import etree

url_list = []  # 用于存放标题和url

# 获取源码
def get_content(url):
	html = requests.get(url).content
	return html

# 获取某页中的所有帖子的url
def get_url(html):
	soup = BeautifulSoup(html, 'lxml')  # lxml是解析方式，第三方库
	blog_url_list = soup.find_all('h2', class_='fn-ellipsis')
	for i in blog_url_list:
		url_list.append([i.find('a').text, i.find('a')['href']])
	# print(url_list)
	last_list.append(url_list)

start_url = 'http://support.i-search.com.cn/recent?p=1'
response = requests.get(start_url)
content = response.text
selector = etree.HTML(content)
maxPage = selector.xpath('//*[@class="pagination"]/a[10]/text()')[0].replace(">>","")
print(maxPage)
for page in range(1, int(maxPage)):
	url = 'http://support.i-search.com.cn/recent?p={}'.format(page)
	get_url(get_content(url))

newTable = '//mac/Home/Desktop/isearch_list2.xls'
wb = xlwt.Workbook(encoding='utf-8')  # 打开一个对象
ws = wb.add_sheet('blog')  # 添加一个sheet
headData = ['标题', '链接']
# 写标题
for colnum in range(0, 2):
	ws.write(0, colnum, headData[colnum], xlwt.easyxf('font:bold on'))  # 第0行的第colnum列写入数据headDtata[colnum]，就是表头，加粗
index = 1
lens = len(url_list)
# 写内容
for j in range(0, lens):
	ws.write(index, 0, url_list[j][0])
	ws.write(index, 1, url_list[j][1])
	index += 1  # 下一行
wb.save(newTable)  # 保存

实现结果如下图所示：