Using java to call python's crawler is a very interesting thing, but most of the solutions are not reliable. The author spent two days, hands-on practice, and finally completely solved the problem

java-python

Problems to be solved when Java calls Python crawler:

Parameter passing problem

Problems with dependent packages

java and python data transfer

import java.io.IOException;
import java.io.File;

public class BPython {
    public static void main(String[] args) {
        // Get current path
        File directory = new File("");//Set as current folder
        String dirPath = directory.getAbsolutePath();//Get absolute path
        Process proc;
        try {
            // python interpreter path
            String pyPath = "/Users/lijianzhao/.virtualenvs/py3/bin/python3";
            // python script file path
            String pyFilePath = dirPath+ "/bdindex.py";
            System.out.println(pyFilePath);
            // Parameters passed to python
            String argv1 = "Under one man";
            proc = Runtime.getRuntime().exec(pyPath + " "+ pyFilePath + " " +argv1);
            proc.waitFor();
        } catch (IOException e) {
            e.printStackTrace();
        } catch (InterruptedException e) {
            e.printStackTrace();
        }
    }
}

# coding=utf-8

import requests
from lxml import etree
import os
import sys

def getData(wd):
    # Set user agent header
    headers = {
        # Set user agent header (put sheepskin on wolf)
        "User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_6) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36",
    }
    # Construct target web address
    target_url = "https://www.baidu.com/s?wd="+str(wd)
    # Get response
    data = requests.get(target_url, headers = headers)
    # xpath formatting
    data_etree = etree.HTML(data.content)
    # Extract data list
    content_list = data_etree.xpath('//div[@id="content_left"]/div[contains(@class, "result c-container")]')
    # Define the returned string
    result = ""
    # Get title, content, link
    for content in content_list:
        result_title = "<Title>  "
        bd_title = content.xpath('.//h3/a')
        for bd_t in bd_title:
            result_title += bd_t.xpath('string(.)')

        result_content = "<content>"
        bd_content = content.xpath('.//div[@class="c-abstract"]')
        for bd_c in bd_content:
            result_content += bd_c.xpath('string(.)')
        try:
            result_link = "<link>"+str(list(content.xpath('.//div[@class="f13"]/a[@class="c-showurl"]/@href'))[0])
        except:
            result_link = "<link>: empty"

        result_list = [result_title, "\n" , result_content , "\n", result_link]
        for result_l in result_list:
            result += str(result_l)
    return result


# Save as file
def saveDataToFile(file_name, data):
    # Create folder
    if os.path.exists("./data/"):
        pass
    else:
        os.makedirs("./data/")
    with open("./data/"+file_name+".txt", "wb+") as f:
        f.write(data.encode())

def main():
    wd = ""
    print(wd)
    try:
        wd = sys.argv[1]
    except:
        pass

    if (len(wd) == 0):
        wd = "Hello"

    str_data = getData(wd)   

    saveDataToFile(wd, str_data)
    print("end")


if __name__ == '__main__':
    main()