Question

我有一份专利号码电子表格，我可以通过抓取Google专利，USPTO网站和其他一些数据来获取额外数据。我大部分都在跑步，但有一件事我整天都被困住了。当我去美国专利商标局网站并获得源代码时，它有时会给我整个事情并且工作得非常好，但有时候它只给我关于下半部分（我在寻找的是第一部分）。

在这里搜索了很多，我还没有看到有这个问题的人。这是相关的一段代码（由于我现在已经尝试解决这个问题，但它有一些冗余，但我确信这是最少的其问题）：

from bs4 import BeautifulSoup
import html5lib
import re
import csv
import urllib
import requests

# This is the base URL for Google Patents
gpatbase = "https://www.google.com/patents/US"
ptobase = "http://patft.uspto.gov/netacgi/nph-Parser?Sect2=PTO1&Sect2=HITOFF&p=1&u=/netahtml/PTO/search-bool.html&r=1&f=G&l=50&d=PALL&RefSrch=yes&Query=PN/"

# Bring in the patent numbers and define the writer we'll use to add the new info we get
with open(r'C:\Users\Filepathblahblahblah\Patent Data\scrapeThese.csv', newline='') as csvfile:
patreader = csv.reader(csvfile)
writer = csv.writer(csvfile)

for row in patreader:
    patnum = row[0]
    #print(row)

    print(patnum)
    # Take each patent and append it to the base URL to get the actual one
    gpaturl = gpatbase + patnum
    ptourl = ptobase + patnum


    gpatreq = requests.get(gpaturl)
    gpatsource = gpatreq.text
    soup = BeautifulSoup(gpatsource, "html5lib")

    # Find the number of academic citations on that patent

    # From the Google Patents page, find the link labeled USPTO and extract the url
    for tag in soup.find_all("a"):
        if tag.next_element == "USPTO":
            uspto_link = tag.get('href')

    #uspto_link = ptourl
    requested = urllib.request.urlopen(uspto_link)
    source = requested.read()

    pto_soup = BeautifulSoup(source, "html5lib")

    print(uspto_link)
    # From the USPTO page, find the examiner's name and save it
    for italics in pto_soup.find_all("i"):
        if italics.next_element == "Primary Examiner:":
            prim = italics.next_element
        else:
            prim = "Not found"

    if prim != "Not found":
        examiner = prim.next_element
    else:
        examiner = "Not found"

    print(examiner)

截至目前，关于我是否会获得考官姓名或者未找到考试名称大约50-50，＆＃34;而且我也看不到任何一个小组的成员彼此有共同之处，所以我完全没有想法。

Answer 1

我仍然不知道是什么导致了这个问题，但如果有人遇到类似的问题，我就能找到解决方法。如果您将源代码发送到文本文件而不是尝试直接使用它，它将不会被切断。我想问题是在数据下载之后，但在导入到“工作区”之前。这是我在刮刀中写的代码片段：

 if examiner == "Examiner not found":
        filename = r'C:\Users\pathblahblahblah\Code and Output\Scraped Source Code\scraper_errors_' + patnum + '.html'
        sys.stdout = open(filename, 'w')
        print(patnum)
        print(pto_soup.prettify())
        sys.stdout = console_out

        # Take that logged code and find the examiner name
        sec = "Not found"
        prim = "Not found"
        scraped_code = open(r'C:\Users\pathblahblahblah\Code and Output\Scraped Source Code\scraper_errors_' + patnum + '.txt')

        scrapedsoup = BeautifulSoup(scraped_code.read(), 'html5lib')
        # Find all italics (<i>) tags
        for italics in scrapedsoup.find_all("i"):
            for desc in italics.descendants:
                # Check to see if any of them affect the words "Primary Examiner"
                if "Primary Examiner:" in desc:
                    prim = desc.next_element.strip()
                    #print("Primary found: ", prim)
                else:
                    pass
                # Same for "Assistant Examiner"
                if "Assistant Examiner:" in desc:
                    sec = desc.next_element.strip()
                    #print("Assistant found: ", sec)
                else:
                    pass

        # If "Secondary Examiner" in there, set 'examiner' to the next string 
        # If there is no secondary examiner, use the primary examiner
        if sec != "Not found":
            examiner = sec
        elif prim != "Not found":
            examiner = prim
        else:
            examiner = "Examiner not found"
        # Show new results in the console
        print(examiner)

Python网络爬虫有时会返回一半的源代码，有时候全部都会返回...来自同一个网站

1 个答案: