Changeset 783
- Timestamp:
- 06/20/07 05:45:15 (6 years ago)
- Files:
-
- 2 modified
-
grabbers/abc_website (modified) (3 diffs)
-
status (modified) (1 diff)
Legend:
- Unmodified
- Added
- Removed
-
grabbers/abc_website
r766 r783 490 490 } else { 491 491 if ((!$opt_cheap) && ($unprocessed_url[$i] ne "")) { 492 $stats{portal_detail_pages}++;493 492 &get_one_abc_event($cache_key, $unprocessed_url[$i]); 494 493 … … 531 530 { 532 531 my ($cache_key, $url) = @_; 532 533 if ($stats{failed_to_fetch_portal_detail_page} >= 3 or $stats{failed_to_parse_portal_detail_page} >= 9) 534 { 535 &log("Skipping detail page because too many failures."); 536 return; 537 } 538 533 539 my $seen_programme = 0; 534 535 540 my $data = Shepherd::Common::get_url(url => $url, debug => $debug); 536 541 my $tree = HTML::TreeBuilder->new_from_content($data) if ($data); 537 542 if (!defined $tree) { 538 543 &log("failed to fetch $url; skipping"); 544 $stats{failed_to_fetch_portal_detail_page}++; 539 545 return; 540 546 } … … 621 627 printf "WARNING: failed to parse any programme data from '%s' - blocked/rate-limited/format-changed?\n",$url; 622 628 $stats{failed_to_parse_portal_detail_page}++; 623 } 629 return; 630 } 631 $stats{portal_detail_pages}++; 624 632 } 625 633 -
status
r782 r783 5 5 grabber yahoo7widget 1.86 6 6 grabber rex 3.5.5 7 grabber abc_website 3.0 47 grabber abc_website 3.05 8 8 grabber sbsnews_website 0.16 9 9 grabber oztivo 1.00
