web: epaper.jinghua.cn/html
write download .py ,
during the fetch the rss,problems appears
News from jhsb
Resolved conversion options
calibre version: 0.8.14
{'asciiize': False,
'author_sort': None,
'authors': None,
'base_font_size': 0,
'book_producer': None,
'change_justification': 'original',
'chapter': None,
'chapter_mark': 'pagebreak',
'comments': None,
'cover': None,
'debug_pipeline': None,
'dehyphenate': True,
'delete_blank_paragraphs': True,
'disable_font_rescaling': False,
'dont_compress': False,
'dont_download_recipe': False,
'duplicate_links_in_toc': False,
'enable_heuristics': False,
'extra_css': None,
'extract_to': None,
'fix_indents': True,
'font_size_mapping': None,
'format_scene_breaks': True,
'html_unwrap_factor': 0.4,
'input_encoding': None,
'input_profile': <calibre.customize.profiles.InputProfile object at 0x040A2270>,
'insert_blank_line': False,
'insert_blank_line_size': 0.5,
'insert_metadata': False,
'isbn': None,
'italicize_common_cases': True,
'keep_ligatures': False,
'kindlegen': False,
'language': None,
'level1_toc': None,
'level2_toc': None,
'level3_toc': None,
'line_height': 0,
'linearize_tables': False,
'lrf': False,
'margin_bottom': 5.0,
'margin_left': 5.0,
'margin_right': 5.0,
'margin_top': 5.0,
'markup_chapter_headings': True,
'max_toc_links': 50,
'minimum_line_height': 120.0,
'mobi_ignore_margins': False,
'mobi_toc_at_start': False,
'no_chapters_in_toc': False,
'no_inline_navbars': True,
'no_inline_toc': False,
'output_profile': <calibre.customize.profiles.KindleOutput object at 0x040A2590>,
'page_breaks_before': None,
'password': None,
'personal_doc': '[PDOC]',
'prefer_author_sort': False,
'prefer_metadata_cover': False,
'pretty_print': False,
'pubdate': None,
'publisher': None,
'rating': None,
'read_metadata_from_opf': None,
'remove_fake_margins': True,
'remove_first_image': False,
'remove_paragraph_spacing': False,
'remove_paragraph_spacing_indent_size': 1.5,
'renumber_headings': True,
'replace_scene_breaks': '',
'rescale_images': False,
'series': None,
'series_index': None,
'smarten_punctuation': False,
'sr1_replace': '',
'sr1_search': '',
'sr2_replace': '',
'sr2_search': '',
'sr3_replace': '',
'sr3_search': '',
'tags': None,
'test': False,
'timestamp': None,
'title': None,
'title_sort': None,
'toc_filter': None,
'toc_threshold': 6,
'toc_title': None,
'unwrap_lines': True,
'use_auto_toc': False,
'username': None,
'verbose': 2}
InputFormatPlugin: Recipe Input running
Python function terminated unexpectedly
HTTP Error 403: Forbidden (Error Code: 1)
Traceback (most recent call last):
File "site.py", line 132, in main
File "site.py", line 109, in run_entry_point
File "site-packages\calibre\utils\ipc\worker.py", line 181, in main
File "site-packages\calibre\gui2\convert\gui_conversion.py", line 25, in gui_convert
File "site-packages\calibre\ebooks\conversion\plumber.py", line 937, in run
File "site-packages\calibre\customize\conversion.py", line 204, in __call__
File "site-packages\calibre\web\feeds\input.py", line 105, in convert
File "site-packages\calibre\web\feeds\news.py", line 737, in download
File "site-packages\calibre\web\feeds\news.py", line 874, in build_index
File "c:\docume~1\admini~1\locals~1\temp\calibre_0.8.14 _tmp_syu1qu\siuyys_recipes\recipe0.py", line 29, in parse_index
soup = self.index_to_soup(cat)
File "site-packages\calibre\web\feeds\news.py", line 498, in index_to_soup
File "site-packages\mechanize-0.2.4-py2.7.egg\mechanize\_mechanize.py", line 199, in open_novisit
File "site-packages\mechanize-0.2.4-py2.7.egg\mechanize\_mechanize.py", line 255, in _mech_open
mechanize._response.httperror_seek_wrapper: HTTP Error 403: Forbidden
script is:
from calibre.web.feeds.news import BasicNewsRecipe
import re
class jhsb(BasicNewsRecipe):
title = u'jhsb'
__author__ = 'zyl'
language = 'zh'
oldest_article = 7
max_articles_per_feed = 100
no_stylesheets = True
cover_url = 'http://epaper.jinghua.cn/tplimg/logo_080715.gif'
language = 'zh'
keep_only_tags = []
keep_only_tags.append(dict(name = 'div', attrs = {'class': 'new_b_b_b'}))
def parse_index(self):
catnames = {}
catnames["http://epaper.jinghua.cn/html/"] = ""
feeds = []
for cat in catnames.keys():
articles = []
soup = self.index_to_soup(cat)
for a in soup.findAll('a',attrs={'href' : re.compile(cat+"201[0-9]-[0-1][0-9]/[0-1][0-9]/[0-9][0-9][0-9][0-9][0-9][0-9].html")}):
url = a['href'].strip()
myarticle=({'title':self.tag_to_string(a), 'url':url, 'description':'', 'date':''})
self.log("found %s" % url)
articles.append(myarticle)
self.log("Adding URL %s\n" %url)
if articles:
feeds.append((catnames[cat], articles))
return feeds
how to avoid the "HTTP Error 403: Forbidden"?
please help me.
.