Python之JavaScript逆向系列——4、Body

pip install parsel

from parsel import Parser, urlopen

# 创建一个解析器对象
p = Parser()

# 发送HTTP GET请求到指定的URL
response = urlopen("http://example.com")

# 解析响应体
doc = p.parse(response.text)

# 遍历并打印出所有链接
for link in doc.links:
    print(link)

from parsel import Parser, urlopen, Request

p = Parser()

url = "http://example.com/api"
data = {"key1": "value1", "key2": "value2"}
request = Request(url=url, method="POST", data=data)
response = urlopen(request)
doc = p.parse(response.text)

from parsel import Selector, urlopen

doc = Selector(text=urlopen("http://example.com/page.html").text)
print(doc.select("div.content"))  # 选择所有class为"content"的div元素

import re
from parsel import Parser, urlopen, Selector, re_type_matches_named_group

doc = Selector(text=urlopen("http://example.com/page.html").text)
data = doc.text_content().strip()  # 提取文本内容，移除前后的空白字符
match = re.search(r"your-regex-pattern", data)  # 使用正则表达式匹配数据
if match and re_type_matches_named_group(match):  # 如果匹配成功并且使用了命名捕获组，提取匹配到的值
    print(match.group('named-group'))  # 输出匹配到的值名称为'named-group'的值

def GetUrl(url):
    try:
        html = requests.get(url, headers=headers)
        sel = parsel.Selector(html.text)
        # 获取主Title
        mTitle.append(sel.css(".book-meta h1::text").getall()[0])
        href = sel.css(".volume-list ul a::attr(href)").getall()
        # 获取标题
        text = sel.css(".volume-list ul a::text").getall()
        for item1, item2 in zip(href, text):
            a_href_list = ["", ""]
            a_href_list[0] = item1
            a_href_list[1] = item2
            a_href_arr.append(a_href_list)
        print("列表获取完毕")
    except:
        print("解析异常")