import requests
import re
import os
from multiprocessing.dummy import Pool
start_url = 'https://www.xbiquge.la/58/58814/'
def get_source(url):
"""
获取网页源代码。
"""
html = requests.get(url)
return html.content.decode('utf-8')
def get_toc(html):
"""
获取每一章链接,储存到一个列表中并返回。
"""
toc_url_list = []
toc_block = re.findall('<dl>(.*?)<div id="footer"', html, re.S)[0]
toc_url = re.findall("href='(.*?)'", toc_block, re.S)
for url in toc_url:
toc_url_list.append(start_url + url)
return toc_url_list
def get_article(html):
"""
获取每一章的正文并返回章节名和正文。
"""
chapter_name = re.search('<title>(.*?)</title>', html, re.S).group(1)
text_block = re.search('<div id="content">(.*?)</p></div>', html, re.S).group(1)
text_block = text_block.replace('<br />', '')
return chapter_name, text_block
def save(chapter, article):
"""
将每一章保存到本地。
"""
os.makedirs('白骨大圣', exist_ok=True)
with open(os.path.join('白骨大圣', chapter + '.txt'), 'w', encoding='utf-8') as f:
f.write(article)
def query_article(url):
"""
根据正文网址获取正文源代码,并调用get_article函数获得正文内容最后保存到本地。
"""
article_html = get_source(url)
chapter_name, article_text = get_article(article_html)
save(chapter_name, article_text)
if __name__ == '__main__':
toc_html = get_source(start_url)
toc_list = get_toc(toc_html)
pool = Pool(4)
pool.map(query_article, toc_list)
1.增加headers请求头,2 章节网址要改下,3.在text_block部分加上try/except异常处理,防止有的不存在。
经修改后可正常运行的代码:
import requests
import re
import os
from multiprocessing.dummy import Pool
headers={'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/93.0.4577.63 Safari/537.36 Edg/93.0.961.38'}
start_url = 'https://www.xbiquge.la/58/58814'
def get_source(url):
"""
获取网页源代码。
"""
html = requests.get(url,headers=headers)
return html.content.decode('utf-8')
def get_toc(html):
"""
获取每一章链接,储存到一个列表中并返回。
"""
toc_url_list = []
toc_block = re.findall('<dl>(.*?)<div id="footer"', html, re.S)[0]
toc_url = re.findall("href='(.*?)'", toc_block, re.S)
for url in toc_url:
toc_url_list.append('https://www.xbiquge.la' + url)
return toc_url_list
def get_article(html):
"""
获取每一章的正文并返回章节名和正文。
"""
chapter_name = re.search('<title>(.*?)</title>', html, re.S).group(1)
try:
text_block = re.search('<div id="content">(.*?)</p></div>', html, re.S).group(1)
text_block = text_block.replace('<br />', '')
except:text_block=''
return chapter_name, text_block
def save(chapter, article):
"""
将每一章保存到本地。
"""
os.makedirs('白骨大圣', exist_ok=True)
with open(os.path.join('白骨大圣', chapter + '.txt'), 'w', encoding='utf-8') as f:
f.write(article)
def query_article(url):
"""
根据正文网址获取正文源代码,并调用get_article函数获得正文内容最后保存到本地。
"""
article_html = get_source(url)
chapter_name, article_text = get_article(article_html)
save(chapter_name, article_text)
if __name__ == '__main__':
toc_html = get_source(start_url)
toc_list = get_toc(toc_html)
pool = Pool(4)
pool.map(query_article, toc_list)
如有帮助,请点击我回答的右上方采纳按钮给予采纳。
章节网址处理的有问题