def getNextPage(html):
"""获取下一页地址，如果没有，返回None"""
next_url = '<div class="wp-pagenavi">.*<a href="(.*?)">下一页</a>'
next_url = parse(html, next_url)
if len(next_url) > 0:
return next_url[0]
else:
return None
BASE_DIR = getBaseDir() + "\\txt\\"
def getAuthor(html):
regex_author = '<h1>.*?</h1>.*?<p>.*?：(.*?)</p>'
author = re.findall(regex_author, html, re.S)
return author[0]
book_url = "https://www.dhzw.org/book/13/13766/"
prefix = 'https://www.dhzw.org/book/13/13766/'
html = getHtmlByUrl(book_url)
book_name_regex = '<h1>(.*?)</h1>'
result = parse(html, book_name_regex)
isNull(result)
book_name = result[0]
print(book_name)
book_txt = BASE_DIR + book_name + '.txt'
book_catalog_txt = BASE_DIR + book_name + "_catalog.txt"
# deleteFile(book_txt)
# deleteFile(book_catalog_txt)
catalog_all_regex = '<dl>(.*?)</dl>'
result = parse(html, catalog_all_regex)
isNull(result)
catalogs_regex = '<dd><a href="(.*?)" .*?>(.*?)</a></dd>'
result = parse(result[0], catalogs_regex)
isNull(result)
def formattContent(content):
content = content.replace(' ', '')
content = content.replace('<br />', '')
return content
book_url = "http://www.123xiaoqiang.me/modules/article/reader.php?aid=15767"
prefix = 'http://www.123xiaoqiang.me'
BASE_DIR = getBaseDir()
html = getHtmlByUrl(book_url)
# 获取书名
title_regex = '<h1>(.*?)</h1>'
title_result = parse(html, title_regex)
isNull(title_result)
title = title_result[0]
# 获取作者
author_regex = '<span>作者：(.*?)</span>'
author_result = parse(html, author_regex)
isNull(author_result)
author = '作者：' + author_result[0]
# 获取目录
catalog_div_regex = '<div class="liebiao">(.*?)</div>'
catalog_div_result = parse(html, catalog_div_regex)
isNull(catalog_div_result)
html = catalog_div_result[0]
catalog_regex = '<li><a href="(.*?)">(.*?)</a></li>'
def getPicUrl(html):
"""根据网页获取图片地址"""
pic_url = '<p><img src="(.*?)".*?class="alignnone.*?" /></p>'
pic_url = parse(html, pic_url)
return pic_url
def getPicNum(html):
"""获取图片数量"""
pic_num = '<title>.*\\[(\\d+)P\\].*</title>'
pic_num = parse(html, pic_num)
return pic_num[0]
def getName(html):
"""获取漫画名称"""
name = '<h1 class="entry-title">(.*?)</h1>'
name = parse(html, name)
return name[0]