You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
70 lines
1.9 KiB
70 lines
1.9 KiB
8 months ago
|
import requests
|
||
|
|
from lxml import etree
|
||
|
|
import csv
|
||
|
|
import os
|
||
|
|
|
||
|
|
start_url = 'https://www.xingyueboke.com/sudongpozhuan/'
|
||
|
|
header = {'User-Agent': "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) "
|
||
|
|
"Chrome/123.0.0.0 Safari/537.36 Edg/123.0.0.0"}
|
||
|
|
|
||
|
|
|
||
|
|
def get_source(url=start_url):
|
||
|
|
response = requests.get(url, headers=header)
|
||
|
|
if response.status_code == 200:
|
||
|
|
response.encoding = 'utf-8'
|
||
|
|
return response.text
|
||
|
|
else:
|
||
|
|
print("请求失败，状态码为{}".format(response.status_code))
|
||
|
|
return ""
|
||
|
|
|
||
|
|
|
||
|
|
source = get_source()
|
||
|
|
# print(source)
|
||
|
|
|
||
|
|
|
||
|
|
def get_chapter_urls(start_source):
|
||
|
|
selector = etree.HTML(start_source)
|
||
|
|
urls = selector.xpath('//div[@class="book-list clearfix"]/ul/li/a/@href')
|
||
|
|
rights_urls = []
|
||
|
|
for url in urls:
|
||
|
|
rights_urls.append(url)
|
||
|
|
return rights_urls
|
||
|
|
|
||
|
|
|
||
|
|
url1 = get_chapter_urls(source)
|
||
|
|
# print(url1)
|
||
|
|
|
||
|
|
|
||
|
|
def get_article(article_html):
|
||
|
|
selector = etree.HTML(article_html)
|
||
|
|
title = selector.xpath('//h1/text()')[0]
|
||
|
|
content = selector.xpath('string(//div[@id="nr1"]/div)')
|
||
|
|
return title, content
|
||
|
|
|
||
|
|
|
||
|
|
def save(title, content):
|
||
|
|
filename = "苏东坡传/" + title + ".txt"
|
||
|
|
|
||
|
|
if not os.path.exists("苏东坡传"):
|
||
|
|
os.makedirs("苏东坡传")
|
||
|
|
with open(filename, "w", encoding='utf-8') as f:
|
||
|
|
f.write(content)
|
||
|
|
|
||
|
|
def savaCsv(list):
|
||
|
|
filename = "苏东坡传/苏东坡传.csv"
|
||
|
|
if not os.path.exists("苏东坡传"):
|
||
|
|
os.makedirs("苏东坡传")
|
||
|
|
with open(filename, "w", encoding="utf-8",newline='') as f:
|
||
|
|
w = csv.writer(f)
|
||
|
|
w.writerow(["网页地址", "标题", "正文长度"])
|
||
|
|
w.writerows(list)
|
||
|
|
list =[]
|
||
|
|
for url in url1:
|
||
|
|
article_html = get_source(url)
|
||
|
|
# print(article_html)
|
||
|
|
title, content = get_article(article_html)
|
||
|
|
print(title)
|
||
|
|
list.append([url,title,len(content)])
|
||
|
|
save(title, content)
|
||
|
|
savaCsv(list)
|