1.使用re.findall('<div id="content">(.*?)</div>',requests1_html.content.decode('gbk'),re.S)
down_dz = 'https://XXXXXXX.html'
headers = {'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:105.0) Gecko/20100101 Firefox/105.0'}
requests1_html = requests.get(down_dz, headers=headers)
requests1_html.encoding = 'gbk'
contents = re.findall('<div id="content">(.*?)</div>',requests1_html.content.decode('gbk'),re.S)
for content in contents:
content = str(content).replace('<br />', '')
content = str(content).replace(' ', '')
print(content)
with open('file/test01.txt','a+',encoding='gbk') as test1:
test1.write(content)
注意:content前面要加上str(),做转换
运行结果是
2.使用BeautifulSoup中的find_all也可以达到异曲同工的效果
down_dz = 'https://XXXXXXX.html'
headers = {'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:105.0) Gecko/20100101 Firefox/105.0'}
requests1_html = requests.get(down_dz, headers=headers)
requests1_html.encoding = 'gbk'
soup1 = BeautifulSoup(requests1_html.text, "lxml")
# print(soup1)
for link1 in soup1.find_all(id="content"):
link1 = str(link1).replace('<br>', '')
link1 = link1.replace('<br/>\n', '')
link1 = link1.replace('<br/>', '')
link1 = link1.replace('<div id="content">', '')
link1 = link1.replace(('</div>'), '')
print(link1)
感觉要多几行代码,运行结果如下
注意: for link1 in soup1.find_all(id="content"):
这个是关键