Question

求python中这段代码的注释，急急急!!!

def parse_txt(doc_id):
content_url = 'https://wenku.baidu.com/api/doc/getdocinfo?callback=cb&doc_id=' + doc_id
content = fetch_url(content_url)
md5 = re.findall('"md5sum":"(.*?)"', content)[0]
pn = re.findall('"totalPageNum":"(.*?)"', content)[0]
rsign = re.findall('"rsign":"(.*?)"', content)[0]
content_url = 'https://wkretype.bdimg.com/retype/text/' + doc_id + '?rn=' + pn + '&type=txt' + md5 + '&rsign=' + rsign
content = json.loads(fetch_url(content_url))
result = ''
for item in content:
for i in item['parags']:
result += i['c'].replace('\\r', '\r').replace('\\n', '\n')
return result

def parse_other(doc_id):
content_url = "https://wenku.baidu.com/browse/getbcsurl?doc_id=" + doc_id + "&pn=1&rn=99999&type=ppt"
content = fetch_url(content_url)
url_list = re.findall('{"zoom":"(.*?)","page"', content)
url_list = [item.replace("\\", '') for item in url_list]
if not os.path.exists(doc_id):
os.mkdir(doc_id)
for index, url in enumerate(url_list):
content = session.get(url).content
path = os.path.join(doc_id, str(index) + '.jpg')
with open(path, 'wb') as f:
f.write(content)
print("图片保存在" + doc_id + "文件夹")

Answer 1

这个没缩进看起来累,不过大概意思,而且你少了前面的导入的模块,这是个简单的爬虫把,应该少了导入import request as re,应该就是简单的爬虫超级简单,大概过程我给你讲一下,先找到爬的网址的网址,把网址的f12你看到html格式文本考过来,再找你想要的内容所在文本的格式,批量找到,就这样