爬虫_大众点评文字显示不全_无法复制_文字替换_无法抓取_私活接单

大众点评评论标签替换文字，文字无法显示，无法复制。

思路构造标签对应文字库，爬取网页之后，自己通过文字库，自己处理。

不讲理论，只上代码，如下：（python3）

import math
import re

import requests


def get_css_and_px_dict(con):
    find_datas = re.findall(r'(\.[a-zA-Z0-9-]+)\{background:(\-\d+\.\d+)px (\-\d+\.\d+)px', con)
    css_name_and_px = {}
    for data in find_datas:
        span_class_attr_name = data[0][1:]
        offset = data[1]
        position = data[2]
        css_name_and_px[span_class_attr_name] = [offset, position]
    return css_name_and_px


def get_svg_urls(con):
    find_datas = re.findall(
        r'\[class\^=\"([a-zA-Z0-9-]+)\"\]{[a-zA-Z0-9/.\-: ;_]+\(([a-zA-Z0-9/.\-: ;_]+)\)[a-zA-Z0-9/.\-: ;_]+}', con)
    css_name_and_px = {}
    for data in find_datas:
        url = data[1]
        if url.startswith('//'):
            url = 'http:' + url
        css_name_and_px[data[0]] = url
    return css_name_and_px


def download_content(url):
    return requests.get(url).content.decode("utf-8")


def parse_result(x_src, y_src, svg_content):
    find_datas = re.findall(r'<path id="(\d+)" d="([a-zA-Z0-9 ]+)"/>', svg_content)
    data_mapping = {}
    for d in find_datas:
        target_id, item = d
        _, y_position, _ = item.split(' ')
        data_mapping[y_position] = target_id
    font_size = re.findall(r'font-size:(\d+)px', svg_content)[0]
    find_datas = re.findall(r'<textPath xlink:href="#(\d+)" textLength="\d+">(.*)</textPath>', svg_content)
    data_warehouse = {}
    for d in find_datas:
        target_id, item = d
        data_warehouse[target_id] = item
    x_index = int(int(math.fabs(float(x_src)) / int(font_size)))
    y = int(math.fabs(float(y_src))) + 23
    target_id = data_mapping.get(str(y))
    if target_id is None:
        return
    line = data_warehouse[target_id]
    words = []
    for w in line:
        words.append(w)
    word = words[x_index]
    return word


def work(css_url):
    con = download_content(css_url)
    css_data = get_css_and_px_dict(con)
    svg_urls = get_svg_urls(con)
    print(svg_urls)
    svg_contents = {}
    result_dict = {}
    for prefix, url in svg_urls.items():
        svg_data = download_content(url)
        svg_contents[prefix] = svg_data
    for css_id, position in css_data.items():
        for prefix, content in svg_contents.items():
            if css_id.startswith(prefix):
                x_src, y_src = position
                word = parse_result(x_src, y_src, content)
                result_dict[css_id] = word
    print(result_dict)


def run():
    css_url = 'http://s3plus.meituan.net/v1/mss_0a06a471f9514fc79c981b5466f56b91/svgtextcss/5de9a9098d8d30d7d65f16ab93871bb4.css'
    work(css_url)


if __name__ == '__main__':
    run()

每个网页都有一个css文件，拿该网页css文件作为入口url传入即可。

需要爬大众点评的请联系QQ：739848314，价低质优